Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🚀 CrewAI v0.121 is live! 🚀 This one’s packed with upgrades: 🧠 Reasoning Agents 🚫 Hallucination Guardrail (no-op for now) 📃 Auto Markdown output 📅 Auto date injection in Tasks ⚒️ StagehandTool, MCP integration & more 🪲 Bug fixes + fresh docs! RT please?

joaomdmoura's profile picture

João Moura

23,178 subscribers

13,178 görüntüleme • 1 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Olivia Says profil fotoğrafı
Olivia Says1 yıl önce

How does the hallucination guardrail work?

Alexander Mia profil fotoğrafı
Alexander Mia1 yıl önce

INTRODUCING: Agentic Security - LLM Security Scanner! 🔍 🔑 Features: Scans for prompt injections, jailbreaking & more. Provides detailed reports & options to customize attack rules. 🔗access the GitHub Link ↓

Dave Batista 🐺 profil fotoğrafı
Dave Batista 🐺1 yıl önce

Lets goooo👏👏👏

Jason Kneen profil fotoğrafı
Jason Kneen1 yıl önce

This should not be just Enterprise only, why can't you write an agent to add Pro / Team accounts for smaller teams or solorprenuers who want the enterprise features and will pay for it but don't need the demos and sales pitches. Instant trial and sign up and go.

João Moura profil fotoğrafı
João Moura1 yıl önce

everything I showed on this video is literally free 😅 all you gotta do is create an account on The new version of the studio I demoed is not live for anyone yet

Dakota profil fotoğrafı
Dakota1 yıl önce

👏👏

Nicolas profil fotoğrafı
Nicolas1 yıl önce

Is it possible to use grounded responses from LLMs in CrewAI agents? Or do I still need Serper to get fresh news in my crews?

Mike Schiessl profil fotoğrafı
Mike Schiessl1 yıl önce

I can’t wait to test it out

Vishal profil fotoğrafı
Vishal1 yıl önce

Great update! Reasoning agents and hallucination guardrails will really boost reliability.

Lucas Franco profil fotoğrafı
Lucas Franco1 yıl önce

love the hallucination guardrail concept. what's your approach for detecting when an agent goes off track vs just being creative in its reasoning?

Benzer Videolar

🚀 AG2 v0.11.1 is live! 🖥️ AG-UI Message Streaming – Real-time agent responses in your AG-UI frontends with new event-based streaming architecture. 🌊 A2A Streaming – Full streaming support for Agent-to-Agent communication! LLM text streaming now flows through A2A for real-time responses from remote agents, both server and client-side. 📡 OpenAI – Get more out of OpenAI's latest Responses API with stateful conversations, built-in tools (web search, image gen, apply_patch), reasoning model support, and enhanced cost tracking. Docs: 🛠️🪲 Bug fixes and maintenance #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource #AGUI
0:47

🚀 AG2 v0.11.1 is live! 🖥️ AG-UI Message Streaming – Real-time agent responses in your AG-UI frontends with new event-based streaming architecture. 🌊 A2A Streaming – Full streaming support for Agent-to-Agent communication! LLM text streaming now flows through A2A for real-time responses from remote agents, both server and client-side. 📡 OpenAI – Get more out of OpenAI's latest Responses API with stateful conversations, built-in tools (web search, image gen, apply_patch), reasoning model support, and enhanced cost tracking. Docs: 🛠️🪲 Bug fixes and maintenance #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource #AGUI

AG2

17,537 görüntüleme • 6 ay önce

🚀 Exciting updates from Hippius #SN75 ! We're committed to delivering secure, efficient decentralized storage for our users. 🔹 Launched Rust SDK for seamless Hippius Storage integration ( ) . 🔹 Enhanced website with dynamic pricing comparator vs. multiple providers—see the savings! 🔹 Desktop App Beta drops next week (Windows, Mac, Linux)! Your all-in-one companion: - Auto-encrypt & sync private files with erasure coding. - Effortless public folder sync for publishing websites, blogs, & more. - Built-in wallet for sending/receiving Alpha. - Live notifications on credits, referrals, transfers. - Sub-account management & usage history. Plus, console improvements, bug fixes, hippius blockchain consensus for miner de-registration, and validator upgrades for better concurrency & accuracy. 🌐 #Hippius #DecentralizedStorage
0:43

🚀 Exciting updates from Hippius #SN75 ! We're committed to delivering secure, efficient decentralized storage for our users. 🔹 Launched Rust SDK for seamless Hippius Storage integration ( ) . 🔹 Enhanced website with dynamic pricing comparator vs. multiple providers—see the savings! 🔹 Desktop App Beta drops next week (Windows, Mac, Linux)! Your all-in-one companion: - Auto-encrypt & sync private files with erasure coding. - Effortless public folder sync for publishing websites, blogs, & more. - Built-in wallet for sending/receiving Alpha. - Live notifications on credits, referrals, transfers. - Sub-account management & usage history. Plus, console improvements, bug fixes, hippius blockchain consensus for miner de-registration, and validator upgrades for better concurrency & accuracy. 🌐 #Hippius #DecentralizedStorage

Hippius

16,957 görüntüleme • 1 yıl önce

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.
0:49

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.

Puck

94,213 görüntüleme • 20 gün önce

OpenClaw just made the world's smartest AI model its default brain. And the whole thing is still free. GPT 5.4 is now built in. No extra setup. Just pick OpenAI and go. But that's not even the biggest part of this update. Here's the full stack that just dropped: → Pluggable context engines. You can now swap how your AI remembers things. Like upgrading from a notebook to a filing cabinet. → ACP bindings survive restarts. Your agents reconnect automatically. No more broken workflows at 3am. → Secret ref. Passwords and API keys never sit in plain text again. → Slim Docker builds. Smaller containers. Faster deploys. Lower costs. → Gemini 3.1 Flash Light support. Super fast, super cheap. Perfect for high-volume tasks. → iPhone photos auto-convert. No more "unsupported format" errors. → Hundreds of channel fixes across Telegram, Discord, Slack, WhatsApp, and Signal. 6 months ago, this level of AI infrastructure cost thousands. Now one person can set it up in 10 minutes for $0. Save this. It's the most packed free update you'll see this month.
10:33

OpenClaw just made the world's smartest AI model its default brain. And the whole thing is still free. GPT 5.4 is now built in. No extra setup. Just pick OpenAI and go. But that's not even the biggest part of this update. Here's the full stack that just dropped: → Pluggable context engines. You can now swap how your AI remembers things. Like upgrading from a notebook to a filing cabinet. → ACP bindings survive restarts. Your agents reconnect automatically. No more broken workflows at 3am. → Secret ref. Passwords and API keys never sit in plain text again. → Slim Docker builds. Smaller containers. Faster deploys. Lower costs. → Gemini 3.1 Flash Light support. Super fast, super cheap. Perfect for high-volume tasks. → iPhone photos auto-convert. No more "unsupported format" errors. → Hundreds of channel fixes across Telegram, Discord, Slack, WhatsApp, and Signal. 6 months ago, this level of AI infrastructure cost thousands. Now one person can set it up in 10 minutes for $0. Save this. It's the most packed free update you'll see this month.

Julian Goldie SEO

14,733 görüntüleme • 5 ay önce

🤖🔬 Can AI actually do science end-to-end? 🧠📈 And how would we know when it matches, or surpasses, humans? ⚡🧪 AI is rapidly automating scientific discovery, but benchmarking full-cycle discovery, from 💡 ideation → 🧑‍💻 execution → 📊 conclusions, remains unsolved: 🧐🧐🧐 ❌🛠️ Open-ended discovery → manual validation (costly, unscalable) ❌📏 Metric-driven benchmarks (e.g., MLE-Bench) → convenient but narrow (is higher accuracy really enough?) ❌🤖⚖️ LLM-as-judge → useful, but fundamentally risky if used alone 🔥🚀 Introducing FIRE-Bench🔥: Fullcycle Insight Rediscovery Evaluation 👉🌐 📚✨ A benchmark that turns fresh, human-verified insights from recent 🏆 NeurIPS / ICLR / ICML papers into masked, end-to-end discovery challenges 🧩 🌍🔐 Constrained open-ended discovery–backed by ground truth. 📌 Key takeaways: 1⃣ 📖🧱 Reference-based evaluation still matters: constrained LLM judging helps, but human-grounded references remain essential until agents can consistently match human conclusions 2⃣ 🏆🧠 Expert-validated ground truth: all tasks come from recent NeurIPS / ICLR / ICML papers, with contamination carefully controlled 3⃣ 🔁🎭 Rediscovery, not reproduction: original 🧪 methods, 📊 experiments, 💻 implementations, and 📈 analyses are fully masked to create real discovery challenges 🔑 Key empirical findings: 💡 The "Science Gap" is Real: Even the best setup (Claude Code + Sonnet-4) caps out at an F1 score of 46.7. On hard tasks, agents struggle to break 30 💡 Success is a "Lottery": Performance has incredibly high variance. Reliability is a major unsolved issue. 💡 Coding is no longer the bottleneck; high-level reasoning and analysis are: ~74% of errors stem from flawed planning, not coding ⚙️ How it works: 🔹 Research-Problem Trees: We parse papers into trees (from broad roots to concrete leaves). This allows us to select intermediate nodes that perfectly balance open-ended exploration with verifiable ground truth. 🔹 Claim-Level Evaluation: We match AI conclusions against human conclusions using granular claim decomposition (F1 score). 🔹 Creativity Check: We score false positives to see if agents are finding novel truths (Spoiler🚨: they aren’t creative yet). 🔹 New Diagnostic Taxonomy: failures traced across four stages: 🧠 Planning → 🛠️ Implementation → ▶️ Execution → 🧾 Conclusion 🔹 Additional Analyses: cost efficiency, contamination checks, and more. 👀 The Future: 🚀 Live-FIRE-Bench: a live, continuously updated FIRE-Bench to track real-time progress on the latest research (Newest LLMs should be benchmarked with the newest research) 🚀 Stronger scaffolding (search + planning + coding) 🧠🧰 and converting FIRE-Bench into interactive environments for training research agents 🚀 Toward real creativity: We want better systems that can produce genuinely novel conclusions toward creativity 🎨⏳ 🚀 Better systems 🧠✨ and better benchmarks 📏 must co-evolve 🔄 over time 📜🎥 Paper, video, demo, and research trees: 👉🌐 #AI 🤖 #MachineLearning 📚 #AI4Science 🔬 #LLMs 🧠 #Research 🧪 #AgenticAI 🚀 #FireBench 🔥
0:42

🤖🔬 Can AI actually do science end-to-end? 🧠📈 And how would we know when it matches, or surpasses, humans? ⚡🧪 AI is rapidly automating scientific discovery, but benchmarking full-cycle discovery, from 💡 ideation → 🧑‍💻 execution → 📊 conclusions, remains unsolved: 🧐🧐🧐 ❌🛠️ Open-ended discovery → manual validation (costly, unscalable) ❌📏 Metric-driven benchmarks (e.g., MLE-Bench) → convenient but narrow (is higher accuracy really enough?) ❌🤖⚖️ LLM-as-judge → useful, but fundamentally risky if used alone 🔥🚀 Introducing FIRE-Bench🔥: Fullcycle Insight Rediscovery Evaluation 👉🌐 📚✨ A benchmark that turns fresh, human-verified insights from recent 🏆 NeurIPS / ICLR / ICML papers into masked, end-to-end discovery challenges 🧩 🌍🔐 Constrained open-ended discovery–backed by ground truth. 📌 Key takeaways: 1⃣ 📖🧱 Reference-based evaluation still matters: constrained LLM judging helps, but human-grounded references remain essential until agents can consistently match human conclusions 2⃣ 🏆🧠 Expert-validated ground truth: all tasks come from recent NeurIPS / ICLR / ICML papers, with contamination carefully controlled 3⃣ 🔁🎭 Rediscovery, not reproduction: original 🧪 methods, 📊 experiments, 💻 implementations, and 📈 analyses are fully masked to create real discovery challenges 🔑 Key empirical findings: 💡 The "Science Gap" is Real: Even the best setup (Claude Code + Sonnet-4) caps out at an F1 score of 46.7. On hard tasks, agents struggle to break 30 💡 Success is a "Lottery": Performance has incredibly high variance. Reliability is a major unsolved issue. 💡 Coding is no longer the bottleneck; high-level reasoning and analysis are: ~74% of errors stem from flawed planning, not coding ⚙️ How it works: 🔹 Research-Problem Trees: We parse papers into trees (from broad roots to concrete leaves). This allows us to select intermediate nodes that perfectly balance open-ended exploration with verifiable ground truth. 🔹 Claim-Level Evaluation: We match AI conclusions against human conclusions using granular claim decomposition (F1 score). 🔹 Creativity Check: We score false positives to see if agents are finding novel truths (Spoiler🚨: they aren’t creative yet). 🔹 New Diagnostic Taxonomy: failures traced across four stages: 🧠 Planning → 🛠️ Implementation → ▶️ Execution → 🧾 Conclusion 🔹 Additional Analyses: cost efficiency, contamination checks, and more. 👀 The Future: 🚀 Live-FIRE-Bench: a live, continuously updated FIRE-Bench to track real-time progress on the latest research (Newest LLMs should be benchmarked with the newest research) 🚀 Stronger scaffolding (search + planning + coding) 🧠🧰 and converting FIRE-Bench into interactive environments for training research agents 🚀 Toward real creativity: We want better systems that can produce genuinely novel conclusions toward creativity 🎨⏳ 🚀 Better systems 🧠✨ and better benchmarks 📏 must co-evolve 🔄 over time 📜🎥 Paper, video, demo, and research trees: 👉🌐 #AI 🤖 #MachineLearning 📚 #AI4Science 🔬 #LLMs 🧠 #Research 🧪 #AgenticAI 🚀 #FireBench 🔥

Zhen Wang

13,450 görüntüleme • 6 ay önce

Look ma new Codex Updates! 0.119.0 and 0.120.0 are here. And with it, a HUGE number of quality of life updates and bug fixes! > Hooks now render in a dedicated live area above the composer. They only persist when they have output, so your terminal stays clean. If you're running PreToolUse or PostToolUse hooks, this is a huge readability win. > Hooks are now available again on Windows > CTRL+O copies the last agent output. Small but clutch when you're pulling a code block into another file or chat. > New statusline option: context usage as a graphical bar instead of a percentage. Easier to glance at mid-session when you're trying to gauge how much runway you have left. > Zellij support is here with no scrollback bugs. If you've been stuck on tmux just because Codex was broken in Zellij, you're free now (shout out Felipe Coury 🦀) > Memory extensions just landed. The consolidation agent can now discover plugin folders under memories_extensions/ and read their instructions.md to learn how to interpret new memory sources. Drop a folder in, give it guidance, and the agent picks it up automatically during summarization. No core code changes needed. This is the first real extension point for Codex's memory system, and it opens the door for third-party memory plugins. > Did you know, you can /rename a thread? But what's really cool about that is, after you rename it, you can resume it with the same name, no more UUIDs. codex resume mynewapp or directly from the TUI: /resume mynewapp > Multi agents v2 got an update to tool descriptions More reliable multi agent environments and inter agent communication > You can now enable TUI notifications whether Codex is in focus or not. Modify this in your config: [tui] notification_condition = "always" > MAJOR overhaul to Codex MCP functionality: 1. Codex Tool Search now works with custom MCP servers, so tools can be searched and deferred instead of all being exposed up front. 2. Custom MCP servers can now trigger elicitations, meaning they can stop and ask for user approval or input mid-flow. 3. MCP tool results now preserve richer metadata, which improves app/UI handoff behavior. 4. Codex can now read MCP resources directly, letting apps return resource URIs that the client can actually open. 5. File params for Codex Apps are smoother: local file paths can be uploaded and remapped automatically. 6. Plugin cache refresh and fallback sync behavior are more reliable, especially for custom and curated plugins. > Composer and chat behavior smoother overall, resize bugs remain though. > Realtime v2 got several significant improvements as well. > You're still reading? What a legend. 🫶 npm i -g @openai/codex to update
0:36

Look ma new Codex Updates! 0.119.0 and 0.120.0 are here. And with it, a HUGE number of quality of life updates and bug fixes! > Hooks now render in a dedicated live area above the composer. They only persist when they have output, so your terminal stays clean. If you're running PreToolUse or PostToolUse hooks, this is a huge readability win. > Hooks are now available again on Windows > CTRL+O copies the last agent output. Small but clutch when you're pulling a code block into another file or chat. > New statusline option: context usage as a graphical bar instead of a percentage. Easier to glance at mid-session when you're trying to gauge how much runway you have left. > Zellij support is here with no scrollback bugs. If you've been stuck on tmux just because Codex was broken in Zellij, you're free now (shout out Felipe Coury 🦀) > Memory extensions just landed. The consolidation agent can now discover plugin folders under memories_extensions/ and read their instructions.md to learn how to interpret new memory sources. Drop a folder in, give it guidance, and the agent picks it up automatically during summarization. No core code changes needed. This is the first real extension point for Codex's memory system, and it opens the door for third-party memory plugins. > Did you know, you can /rename a thread? But what's really cool about that is, after you rename it, you can resume it with the same name, no more UUIDs. codex resume mynewapp or directly from the TUI: /resume mynewapp > Multi agents v2 got an update to tool descriptions More reliable multi agent environments and inter agent communication > You can now enable TUI notifications whether Codex is in focus or not. Modify this in your config: [tui] notification_condition = "always" > MAJOR overhaul to Codex MCP functionality: 1. Codex Tool Search now works with custom MCP servers, so tools can be searched and deferred instead of all being exposed up front. 2. Custom MCP servers can now trigger elicitations, meaning they can stop and ask for user approval or input mid-flow. 3. MCP tool results now preserve richer metadata, which improves app/UI handoff behavior. 4. Codex can now read MCP resources directly, letting apps return resource URIs that the client can actually open. 5. File params for Codex Apps are smoother: local file paths can be uploaded and remapped automatically. 6. Plugin cache refresh and fallback sync behavior are more reliable, especially for custom and curated plugins. > Composer and chat behavior smoother overall, resize bugs remain though. > Realtime v2 got several significant improvements as well. > You're still reading? What a legend. 🫶 npm i -g @openai/codex to update

am.will

742,298 görüntüleme • 4 ay önce

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.
0:33

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.

Blaze

55,926 görüntüleme • 3 ay önce

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.
30:12

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Himanshu Kumar

228,497 görüntüleme • 3 ay önce

🔥 $KATA FAM! THIS IS HUGE!🔥🥳 The moment we’ve all been waiting for is finally here… Katana Inu Battle Royale is about to go LIVE. 🚀 PLAYABLE FULL GAME - 20th January! Our Battle Royale mode becomes playable for the first time. That is what the developers said. So hopefully, no delays! 😍 This will be a live test phase, and right after that, we’ll bring the game online for everyone to download and play right away! This isn’t just an update 👉 This is a massive milestone for $KATA ⚔️ WHAT HAPPENS AFTER THE TEST? Once the Battle Royale test is complete, we move fast. Now? 👉 WE’RE ALMOST READY.🔥 4 years of building, grinding, and perfecting 😍 We’ll start integrating our already developed Web3 infrastructure directly into the game, including: 🧠 Web3 Multichain Wallet in our Game 🎮 Player Progression UI UX 🖼️ NFT Purchasing in our Game $KATA burn activation, news coming soon! 🔥 And much more! 🚀 Most of this is already built... now it’s about clean structure, smooth integration, and solid testing! After that… 💰 PLAY-TO-EARN GOES LIVE FOR TESTING - TOGETHER WITH THE COMMUNITY 💎 $KATA TOKEN - WE’RE COOKING 👀🔥 With the game finally ready, unlocks real power: - Web3 gaming launchers - Gaming guilds onboarding - Play-to-Earn & Burn activation - In-game NFT skins & weapons - Play live with our Partners/collabs & more! Let's make $KATA great again! 🗺️ ROADMAP & MILESTONES (STRAIGHT TO THE POINT) The game will be ready now! We will just add more polishing to check every corner! Goal: Make the game GOOD and READY for everyone!😍 Here’s the current estimated roadmap we’re aiming to a better place that deserves! 🔥 JANUARY – FULL POWER MODE - General polishing across the entire game - Activate some new videos - Game/Server testing with all Modes - Server stress tests - Preparing for public access - Steam wishlist push & Epic Games - Improving animations, VFX, and sound FX - Integrating player progression into UI / UX - Pushing $KATA into the spotlight! 🔥 ⚡ FEBRUARY – SCALE & POLISH🚀 - Streamers start testing & mass gameplay sessions - Further polish across gameplay and visuals - Final player progression UI/UX integration - AI bots are fully ready inside the game - Bring the $KATA token more visibility into the Web3 community and Game Launchers with p2e. - Launch our first in-game NFT mint, fully integrated and playable directly inside the game ✍️Deliver on all our promises to holders! Allowing NFTs, including 3D characters and weapons, to finally come to life and be used in actual gameplay Focus on: - Visibility on $KATA & our Game - Real gameplay feedback - Steam wishlists & Getting Players for web3 🚀 MARCH – BOOST GAME READY - Final polishing complete - Public-ready version - Roll out $KATA utility and bring it to a much wider audience - Preparing for Steam / Epic Games launch - Streamers & communities fully activated🚀 Please wishlist Katana Inu on Steam: 📣 MARKETING & PLAYER GROWTH - Collaborations with streamers - $KATA into the focus for more holders - Coverage across multiple social platforms - Playing on different web3 game launchers to bring more players into Katana Inu! What comes next? After mid-March, we’ll share new updates and unveil the plan for the next 3 months! The reason for the delay was simple: Battle Royale is complex - and we refused to rush it. 🔥 DROP YOUR HYPE IN THE COMMENTS, FAM This is just the beginning of Katana Inu’s real journey. We’re giving our best for you, $KATA Fam! ❤️ LET’S BUILD. LET’S PLAY. LET’S WIN. ⚔️🐺🔥
2:00

🔥 $KATA FAM! THIS IS HUGE!🔥🥳 The moment we’ve all been waiting for is finally here… Katana Inu Battle Royale is about to go LIVE. 🚀 PLAYABLE FULL GAME - 20th January! Our Battle Royale mode becomes playable for the first time. That is what the developers said. So hopefully, no delays! 😍 This will be a live test phase, and right after that, we’ll bring the game online for everyone to download and play right away! This isn’t just an update 👉 This is a massive milestone for $KATA ⚔️ WHAT HAPPENS AFTER THE TEST? Once the Battle Royale test is complete, we move fast. Now? 👉 WE’RE ALMOST READY.🔥 4 years of building, grinding, and perfecting 😍 We’ll start integrating our already developed Web3 infrastructure directly into the game, including: 🧠 Web3 Multichain Wallet in our Game 🎮 Player Progression UI UX 🖼️ NFT Purchasing in our Game $KATA burn activation, news coming soon! 🔥 And much more! 🚀 Most of this is already built... now it’s about clean structure, smooth integration, and solid testing! After that… 💰 PLAY-TO-EARN GOES LIVE FOR TESTING - TOGETHER WITH THE COMMUNITY 💎 $KATA TOKEN - WE’RE COOKING 👀🔥 With the game finally ready, unlocks real power: - Web3 gaming launchers - Gaming guilds onboarding - Play-to-Earn & Burn activation - In-game NFT skins & weapons - Play live with our Partners/collabs & more! Let's make $KATA great again! 🗺️ ROADMAP & MILESTONES (STRAIGHT TO THE POINT) The game will be ready now! We will just add more polishing to check every corner! Goal: Make the game GOOD and READY for everyone!😍 Here’s the current estimated roadmap we’re aiming to a better place that deserves! 🔥 JANUARY – FULL POWER MODE - General polishing across the entire game - Activate some new videos - Game/Server testing with all Modes - Server stress tests - Preparing for public access - Steam wishlist push & Epic Games - Improving animations, VFX, and sound FX - Integrating player progression into UI / UX - Pushing $KATA into the spotlight! 🔥 ⚡ FEBRUARY – SCALE & POLISH🚀 - Streamers start testing & mass gameplay sessions - Further polish across gameplay and visuals - Final player progression UI/UX integration - AI bots are fully ready inside the game - Bring the $KATA token more visibility into the Web3 community and Game Launchers with p2e. - Launch our first in-game NFT mint, fully integrated and playable directly inside the game ✍️Deliver on all our promises to holders! Allowing NFTs, including 3D characters and weapons, to finally come to life and be used in actual gameplay Focus on: - Visibility on $KATA & our Game - Real gameplay feedback - Steam wishlists & Getting Players for web3 🚀 MARCH – BOOST GAME READY - Final polishing complete - Public-ready version - Roll out $KATA utility and bring it to a much wider audience - Preparing for Steam / Epic Games launch - Streamers & communities fully activated🚀 Please wishlist Katana Inu on Steam: 📣 MARKETING & PLAYER GROWTH - Collaborations with streamers - $KATA into the focus for more holders - Coverage across multiple social platforms - Playing on different web3 game launchers to bring more players into Katana Inu! What comes next? After mid-March, we’ll share new updates and unveil the plan for the next 3 months! The reason for the delay was simple: Battle Royale is complex - and we refused to rush it. 🔥 DROP YOUR HYPE IN THE COMMENTS, FAM This is just the beginning of Katana Inu’s real journey. We’re giving our best for you, $KATA Fam! ❤️ LET’S BUILD. LET’S PLAY. LET’S WIN. ⚔️🐺🔥

Katana Inu

12,768 görüntüleme • 7 ay önce

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!
0:53

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

86,515 görüntüleme • 3 ay önce

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through OpenClaw🦞's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk
1:25

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through OpenClaw🦞's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk

QVAC

29,259,075 görüntüleme • 1 ay önce

HERMES AGENT SUPPORTS 7 TYPES OF AI AGENTS. EACH ONE TAKES LESS THAN 90 SECONDS TO SET UP. MOST PEOPLE ONLY BUILD THE FIRST ONE. HERE ARE ALL SEVEN AND WHEN TO USE EACH. 1. BASIC AGENT WITH TOOLS your agent with access to terminal, browser, file system, web search, and calendar. it plans and executes tasks on its own. this is what you get on day one. "find flights to Lisbon under $400" "check my calendar and flag conflicts" "search the web for competitor pricing" set in Desktop app / Dashboard: Tools → enable what you need. when to use: single tasks that need tool access. 2. AGENT WITH MCP SERVERS connect your agent to external services. Notion, Google Drive, GitHub, Slack, databases, APIs, any MCP-compatible service. the agent doesn't scrape these services. it interacts through structured APIs. reads your Notion pages. creates GitHub issues. queries your database. sends Slack messages. set in Desktop app / Dashboard: MCP → Add Server. when to use: your workflow lives across multiple platforms. 3. SEQUENTIAL AGENTS (pipeline) one agent finishes. passes output to the next. assembly line for AI. agent 1: scans inbox for leads. agent 2: qualifies leads against criteria. agent 3: drafts outreach emails. in Hermes: cron jobs with wakeAgent gates. agent 1 writes output to a file. agent 2 wakes only when that file has new data. agent 3 wakes when agent 2 is done. each agent = a separate profile with its own model. when to use: multi-step workflows where each step depends on the previous one finishing. 4. PARALLEL EXECUTION AGENTS multiple agents working at the same time. results merge when all finish. "research these 5 competitors in parallel" in Hermes: delegate_task with batch mode. up to 3 sub-agents running in parallel by default. each gets its own clean context. only summaries return to the parent. delegation: model: "deepseek/deepseek-v4" children run cheap. parent synthesizes. when to use: independent tasks that don't depend on each other. research, data gathering, analysis. 5. AGENTS WITH ROUTERS conditions that send tasks down different paths based on the input. "if sales email → SDR profile. if support ticket → support profile. if calendar invite → EA profile." in Hermes: Kanban decompose. the decomposer reads profile descriptions and routes each task to the best-fit agent. or: Chief of Staff profile that triages and assigns to other profiles. when to use: incoming work that needs different specialists based on type. 6. HUMAN IN THE LOOP the agent does the work. asks for your approval before executing. "I drafted this email. approve before I send?" "this command will delete 3 files. proceed?" in Hermes: approvals.mode: manual (default). every dangerous action needs your confirmation. 60-second timeout. fails closed. or smart mode: LLM assesses risk. safe actions auto-approved. dangerous ones ask you. uncertain ones escalate. when to use: tasks where a mistake has real consequences. emails, deployments, financial transactions, public posts. 7. DYNAMIC SUB-AGENT SPAWNING your main agent realizes it needs help and spawns specialized sub-agents on the fly. "build this feature" → parent delegates: → sub-agent 1: research the API docs → sub-agent 2: write the code → sub-agent 3: write the tests in Hermes: delegate_task with role: orchestrator. raise max_spawn_depth for nested delegation. delegation: max_spawn_depth: 2 orchestrator_enabled: true depth 2 with concurrency 3 = up to 9 parallel workers. each level multiplies the spend. raise depth only when you need multi-level trees. when to use: complex tasks where the agent discovers what help it needs during execution. THE PROGRESSION: start with 1 (tools) and 6 (approvals). add 2 (MCP) when you need external services. add 4 (parallel) when tasks take too long one at a time. add 3 (sequential) when you build multi-step pipelines. add 5 (routing) when you run multiple profiles. add 7 (dynamic) when single-agent reasoning falls short. seven types. each under 90 seconds to configure. the value compounds as you stack them. comment AGENTS and I'll send you 3 ready-to-build agent setups that combine these types into real workflows.
1:15

HERMES AGENT SUPPORTS 7 TYPES OF AI AGENTS. EACH ONE TAKES LESS THAN 90 SECONDS TO SET UP. MOST PEOPLE ONLY BUILD THE FIRST ONE. HERE ARE ALL SEVEN AND WHEN TO USE EACH. 1. BASIC AGENT WITH TOOLS your agent with access to terminal, browser, file system, web search, and calendar. it plans and executes tasks on its own. this is what you get on day one. "find flights to Lisbon under $400" "check my calendar and flag conflicts" "search the web for competitor pricing" set in Desktop app / Dashboard: Tools → enable what you need. when to use: single tasks that need tool access. 2. AGENT WITH MCP SERVERS connect your agent to external services. Notion, Google Drive, GitHub, Slack, databases, APIs, any MCP-compatible service. the agent doesn't scrape these services. it interacts through structured APIs. reads your Notion pages. creates GitHub issues. queries your database. sends Slack messages. set in Desktop app / Dashboard: MCP → Add Server. when to use: your workflow lives across multiple platforms. 3. SEQUENTIAL AGENTS (pipeline) one agent finishes. passes output to the next. assembly line for AI. agent 1: scans inbox for leads. agent 2: qualifies leads against criteria. agent 3: drafts outreach emails. in Hermes: cron jobs with wakeAgent gates. agent 1 writes output to a file. agent 2 wakes only when that file has new data. agent 3 wakes when agent 2 is done. each agent = a separate profile with its own model. when to use: multi-step workflows where each step depends on the previous one finishing. 4. PARALLEL EXECUTION AGENTS multiple agents working at the same time. results merge when all finish. "research these 5 competitors in parallel" in Hermes: delegate_task with batch mode. up to 3 sub-agents running in parallel by default. each gets its own clean context. only summaries return to the parent. delegation: model: "deepseek/deepseek-v4" children run cheap. parent synthesizes. when to use: independent tasks that don't depend on each other. research, data gathering, analysis. 5. AGENTS WITH ROUTERS conditions that send tasks down different paths based on the input. "if sales email → SDR profile. if support ticket → support profile. if calendar invite → EA profile." in Hermes: Kanban decompose. the decomposer reads profile descriptions and routes each task to the best-fit agent. or: Chief of Staff profile that triages and assigns to other profiles. when to use: incoming work that needs different specialists based on type. 6. HUMAN IN THE LOOP the agent does the work. asks for your approval before executing. "I drafted this email. approve before I send?" "this command will delete 3 files. proceed?" in Hermes: approvals.mode: manual (default). every dangerous action needs your confirmation. 60-second timeout. fails closed. or smart mode: LLM assesses risk. safe actions auto-approved. dangerous ones ask you. uncertain ones escalate. when to use: tasks where a mistake has real consequences. emails, deployments, financial transactions, public posts. 7. DYNAMIC SUB-AGENT SPAWNING your main agent realizes it needs help and spawns specialized sub-agents on the fly. "build this feature" → parent delegates: → sub-agent 1: research the API docs → sub-agent 2: write the code → sub-agent 3: write the tests in Hermes: delegate_task with role: orchestrator. raise max_spawn_depth for nested delegation. delegation: max_spawn_depth: 2 orchestrator_enabled: true depth 2 with concurrency 3 = up to 9 parallel workers. each level multiplies the spend. raise depth only when you need multi-level trees. when to use: complex tasks where the agent discovers what help it needs during execution. THE PROGRESSION: start with 1 (tools) and 6 (approvals). add 2 (MCP) when you need external services. add 4 (parallel) when tasks take too long one at a time. add 3 (sequential) when you build multi-step pipelines. add 5 (routing) when you run multiple profiles. add 7 (dynamic) when single-agent reasoning falls short. seven types. each under 90 seconds to configure. the value compounds as you stack them. comment AGENTS and I'll send you 3 ready-to-build agent setups that combine these types into real workflows.

YanXbt

17,312 görüntüleme • 1 ay önce

Obsidian 1.8.3 is now available to all for desktop and mobile! - Web viewer. New core plugin lets you open external links within Obsidian on desktop. This makes it easier to read linked content without leaving the app and improves multitasking for web research. The plugin can be enabled manually in settings. - Improved iCloud sync. Obsidian no longer waits to confirm that configuration files have synced. - New mobile onboarding. This guided flow helps new mobile users create and sync a vault. - New "Download attachments for current file" command. Downloads all externally embedded images and replaces the external links with internal embeds. A few notable improvements: - When modifying a numbered list, the numbers are now updated automatically. - Pressing Enter in a multi-line list item now continues the list properly. - New "Insert footnote" command. Footnote autocomplete now provides a fallback to create a new footnote if no match is found. - Tags view now includes search. - File Explorer now includes an option to automatically reveal the active file. - Outline now has an "Auto-scroll to current section" option. - Sync now has a new view option, "Hide my changes," which hides your own file changes in a shared Obsidian sync vault. - Recently used commands now appear at the top of the command palette. - "Search current file" search bar now displays the total number of results. - "Insert template" command now sorts templates by file path and displays folder names. - , , and tags with relative src paths are now rendered in Live Preview and Reading mode. - Graph view no longer considers Canvas files as attachments. See the changelog for dozens more improvements and bug fixes.
0:41

Obsidian 1.8.3 is now available to all for desktop and mobile! - Web viewer. New core plugin lets you open external links within Obsidian on desktop. This makes it easier to read linked content without leaving the app and improves multitasking for web research. The plugin can be enabled manually in settings. - Improved iCloud sync. Obsidian no longer waits to confirm that configuration files have synced. - New mobile onboarding. This guided flow helps new mobile users create and sync a vault. - New "Download attachments for current file" command. Downloads all externally embedded images and replaces the external links with internal embeds. A few notable improvements: - When modifying a numbered list, the numbers are now updated automatically. - Pressing Enter in a multi-line list item now continues the list properly. - New "Insert footnote" command. Footnote autocomplete now provides a fallback to create a new footnote if no match is found. - Tags view now includes search. - File Explorer now includes an option to automatically reveal the active file. - Outline now has an "Auto-scroll to current section" option. - Sync now has a new view option, "Hide my changes," which hides your own file changes in a shared Obsidian sync vault. - Recently used commands now appear at the top of the command palette. - "Search current file" search bar now displays the total number of results. - "Insert template" command now sorts templates by file path and displays folder names. - , , and tags with relative src paths are now rendered in Live Preview and Reading mode. - Graph view no longer considers Canvas files as attachments. See the changelog for dozens more improvements and bug fixes.

Obsidian

118,862 görüntüleme • 1 yıl önce

Andrej Karpathy posted about the new programmable layer developers need to master: agents, subagents, prompts, contexts, memory, hooks, MCP. He said it came with no manual and everyone has to figure out how to hold it. This video is part of that manual. Hooks are one of the most underused features in Cursor and Droid, and they're what separate intentional AI-assisted development from hoping it works in production. After file edit: If the agent touches Rust code, hooks automatically regenerate TypeScript types for the frontend. If it touches TypeScript, ESLint runs with autofix. If it touches backend code, cargo clippy runs. On stop: When the agent finishes, it runs cargo check to validate the build before I even look at the output. 00:00 The problem: manually verifying AI-written code 00:31 Introducing hooks to automate tasks when files change 01:53 How hooks regenerate types for the frontend 02:24 How to set up the cursor.hooks.json file 04:44 Reviewing a more comprehensive hooks plan 05:48 Comparing FactoryDroid hooks vs Cursor hooks 06:45 Implementing the equivalent hooks in FactoryDroid 07:50 AI agent fixes a bug in the build command 08:27 How scaffolding makes the AI agent appear smarter 09:08 Demonstrating the successful hook implementation 09:53 Final insight: It's about providing guardrails, not a smarter AI
10:20

Andrej Karpathy posted about the new programmable layer developers need to master: agents, subagents, prompts, contexts, memory, hooks, MCP. He said it came with no manual and everyone has to figure out how to hold it. This video is part of that manual. Hooks are one of the most underused features in Cursor and Droid, and they're what separate intentional AI-assisted development from hoping it works in production. After file edit: If the agent touches Rust code, hooks automatically regenerate TypeScript types for the frontend. If it touches TypeScript, ESLint runs with autofix. If it touches backend code, cargo clippy runs. On stop: When the agent finishes, it runs cargo check to validate the build before I even look at the output. 00:00 The problem: manually verifying AI-written code 00:31 Introducing hooks to automate tasks when files change 01:53 How hooks regenerate types for the frontend 02:24 How to set up the cursor.hooks.json file 04:44 Reviewing a more comprehensive hooks plan 05:48 Comparing FactoryDroid hooks vs Cursor hooks 06:45 Implementing the equivalent hooks in FactoryDroid 07:50 AI agent fixes a bug in the build command 08:27 How scaffolding makes the AI agent appear smarter 09:08 Demonstrating the successful hook implementation 09:53 Final insight: It's about providing guardrails, not a smarter AI

Ray Fernando

60,928 görüntüleme • 7 ay önce

JUST IN: Perplexity launched "Perplexity Computer" — and it might be the most complete AI agent system available right now. Not a chatbot upgrade. Not a research tool with a new name. A system that plans entire projects, delegates to specialist AI models, and runs autonomously for hours, days, or months (their words). Here's what makes the architecture genuinely different: → Opus 4.6 handles core reasoning and orchestration → Gemini handles deep research (spawning its own sub-agents) → Grok handles lightweight speed tasks → Veo 3.1 handles video generation → Nano Banana handles image creation → ChatGPT 5.2 handles long-context recall and wide search → You can override model choices per subtask 19 models total. Each task runs in an isolated environment with a real filesystem, real browser, and real tool integrations. You describe an outcome. It breaks it into tasks and subtasks, creates sub-agents for each, and coordinates them automatically. When a sub-agent hits a problem, it spawns more sub-agents to solve it. And it connects to your existing stack — GitHub, Google Drive, Gmail, Slack, Jira, Linear, Notion, Confluence, Ahrefs, Airtable, and more. Critically, it doesn't just run once. It can run on a schedule. Reading your docs, checking your project boards, pulling from your CRM, and acting on what it finds. Market monitoring. Competitor tracking. Weekly reports with charts. Content pipelines. CRON jobs that actually execute. Not "AI that helps you once." AI that runs in the background for days or months. Think of it as managed OpenClaw — similar autonomous capability (scheduled tasks, multi-step workflows, tool integrations) but fully managed. No Mac Mini. No security config. No infrastructure to maintain. I tested it with a complex prompt — a full stock trading simulator with what-if scenarios, correlation heatmaps, sentiment analysis, and a Bloomberg Terminal aesthetic. Two prompts later: deployed to Netlify via GitHub, with working CRON jobs updating live data. I've started using it to analyze my portfolio. But coding is just one lane. This thing researches, writes reports, generates datasets, creates videos, processes documents, and connects to your existing tools — all in one coordinated workflow. The real shift: you don't choose a model anymore. You describe what you need. The system routes each piece of work to whichever model does it best — and spawns new agents when it hits a wall. 19 models, dynamic sub-agents, scheduled tasks, and your entire tool stack connected. Thoughts?
0:37

JUST IN: Perplexity launched "Perplexity Computer" — and it might be the most complete AI agent system available right now. Not a chatbot upgrade. Not a research tool with a new name. A system that plans entire projects, delegates to specialist AI models, and runs autonomously for hours, days, or months (their words). Here's what makes the architecture genuinely different: → Opus 4.6 handles core reasoning and orchestration → Gemini handles deep research (spawning its own sub-agents) → Grok handles lightweight speed tasks → Veo 3.1 handles video generation → Nano Banana handles image creation → ChatGPT 5.2 handles long-context recall and wide search → You can override model choices per subtask 19 models total. Each task runs in an isolated environment with a real filesystem, real browser, and real tool integrations. You describe an outcome. It breaks it into tasks and subtasks, creates sub-agents for each, and coordinates them automatically. When a sub-agent hits a problem, it spawns more sub-agents to solve it. And it connects to your existing stack — GitHub, Google Drive, Gmail, Slack, Jira, Linear, Notion, Confluence, Ahrefs, Airtable, and more. Critically, it doesn't just run once. It can run on a schedule. Reading your docs, checking your project boards, pulling from your CRM, and acting on what it finds. Market monitoring. Competitor tracking. Weekly reports with charts. Content pipelines. CRON jobs that actually execute. Not "AI that helps you once." AI that runs in the background for days or months. Think of it as managed OpenClaw — similar autonomous capability (scheduled tasks, multi-step workflows, tool integrations) but fully managed. No Mac Mini. No security config. No infrastructure to maintain. I tested it with a complex prompt — a full stock trading simulator with what-if scenarios, correlation heatmaps, sentiment analysis, and a Bloomberg Terminal aesthetic. Two prompts later: deployed to Netlify via GitHub, with working CRON jobs updating live data. I've started using it to analyze my portfolio. But coding is just one lane. This thing researches, writes reports, generates datasets, creates videos, processes documents, and connects to your existing tools — all in one coordinated workflow. The real shift: you don't choose a model anymore. You describe what you need. The system routes each piece of work to whichever model does it best — and spawns new agents when it hits a wall. 19 models, dynamic sub-agents, scheduled tasks, and your entire tool stack connected. Thoughts?

Paweł Huryn

219,681 görüntüleme • 5 ay önce

Expand the Crypto Culture. NYKO 3.0 represents a significant leap forward in democratizing AI-powered content creation within the crypto ecosystem. By combining advanced generation capabilities with social integration and collaborative features, we're building the foundation for a new era of decentralized creative expression. This version will include - video generation - NFT minting - External agent collaboration - Creative topic dashboard - Invite-based rewards - X integration, and more. NYKO is your go-to tool and community for AI-powered creative work. Thousands of creators are already on NYKO, producing hundreds of creative components that inspire fresh, crypto-native content. Even if visual creation isn’t your strong suit, NYKO makes it easy, you’ll discover powerful tools, fun creative prompts, and like-minded creators who’ll get your ideas flowing in no time. Whether you’re expanding existing narratives or starting new ones, NYKO helps you build crypto culture. NYKO rewards both creators and stakers. Our ongoing PRIMEDATA program airdrops millions of $NYKO to creators every week, based on your creative output and Twitter activity. We also run periodic airdrops of bonus tokens to $NYKO stakers. So far, over 20,000,000 tokens have been airdropped. *But please note: selling or unstaking $NYKO may result in being disqualified from receiving rewards. Stake 75k $NYKO now to unlock weekly free credits and start earning PRIMEDATA rewards! And it's alot of fun! 📄 Docs: 🎨 App:
0:43

Expand the Crypto Culture. NYKO 3.0 represents a significant leap forward in democratizing AI-powered content creation within the crypto ecosystem. By combining advanced generation capabilities with social integration and collaborative features, we're building the foundation for a new era of decentralized creative expression. This version will include - video generation - NFT minting - External agent collaboration - Creative topic dashboard - Invite-based rewards - X integration, and more. NYKO is your go-to tool and community for AI-powered creative work. Thousands of creators are already on NYKO, producing hundreds of creative components that inspire fresh, crypto-native content. Even if visual creation isn’t your strong suit, NYKO makes it easy, you’ll discover powerful tools, fun creative prompts, and like-minded creators who’ll get your ideas flowing in no time. Whether you’re expanding existing narratives or starting new ones, NYKO helps you build crypto culture. NYKO rewards both creators and stakers. Our ongoing PRIMEDATA program airdrops millions of $NYKO to creators every week, based on your creative output and Twitter activity. We also run periodic airdrops of bonus tokens to $NYKO stakers. So far, over 20,000,000 tokens have been airdropped. *But please note: selling or unstaking $NYKO may result in being disqualified from receiving rewards. Stake 75k $NYKO now to unlock weekly free credits and start earning PRIMEDATA rewards! And it's alot of fun! 📄 Docs: 🎨 App:

Niyoko

58,059 görüntüleme • 1 yıl önce

I spent 1 day building something that saves you 2-4 weeks. Let me explain. Right now, if you want to deploy a single AI agent that earns money on blockchain, you need: → Wallet infrastructure (key generation, encryption, signing) → Payment integration (on-chain flows, stablecoin handling) → On-chain identity (NFT registration, metadata, URIs) → Escrow contracts (state machines, fund locking) → Monitoring dashboard (analytics, revenue tracking) That's 2-4 weeks of engineering. Minimum. And it locks out 99% of potential creators who aren't Solidity devs. So I built Bumi Agent. It takes 10 seconds. 3 fields: Name, Template, Price. 1 button: Deploy. That's it. Your AI agent is live on Celo, earning cUSD, with on-chain identity before your coffee gets cold. Here's what happens behind that 1 click: • Wallet auto-generated with AES-256-GCM encryption • Agent registered as NFT via ERC-8004 • Payment endpoint configured via x402 protocol • Agent runtime deployed with your chosen template • Revenue starts flowing in cUSD from call #1 No Solidity. No wallet setup. No payment gateway. But the real magic is what powers the agents: 8 AI models with intelligent routing: - Free tier: Claude 4.6 Sonnet, DeepSeek R1, Gemini Flash, Llama 4 Scout, Mistral Medium - Premium: GPT-4o, Gemini 2.5 Pro, Claude 4 Opus If one model fails? Auto-fallback to the next. Zero downtime. Users always get a response. And agents don't just chat they work. ERC-8183 job escrow lets clients post paid tasks: Client funds escrow → Agent delivers → Client approves → Funds release. Fully trustless. On-chain. With Celoscan links for every transaction. The part I'm most proud of: EarthPool 🌱 15% of premium revenue automatically goes to an on-chain ReFi treasury that funds environmental campaigns on Celo. AI growth funding climate action. No greenwashing — every cent is trackable on-chain. The numbers so far: → 12 agents deployed on Celo Mainnet → 52+ paid API calls processed → 7.80 cUSD revenue generated → 3 smart contracts verified on Celoscan → 8 AI models running → 85 contract tests passing → 16 API endpoints in production → 10 agent templates ready The full stack: Frontend: Next.js 16 + Tailwind v4 + Recharts → Vercel Backend: Hono + Drizzle + PostgreSQL + Redis → Railway Blockchain: Solidity 0.8.25 + Foundry + OpenZeppelin → Celo Mainnet Everything is live. Everything is open source. 🌐 📦 📊 Bumi Agent — AI agents for everyone. Built with 🌱 on Celo CeloDevs CeloPublicGoods /disclosure this post is hackathon submission req
7:44

I spent 1 day building something that saves you 2-4 weeks. Let me explain. Right now, if you want to deploy a single AI agent that earns money on blockchain, you need: → Wallet infrastructure (key generation, encryption, signing) → Payment integration (on-chain flows, stablecoin handling) → On-chain identity (NFT registration, metadata, URIs) → Escrow contracts (state machines, fund locking) → Monitoring dashboard (analytics, revenue tracking) That's 2-4 weeks of engineering. Minimum. And it locks out 99% of potential creators who aren't Solidity devs. So I built Bumi Agent. It takes 10 seconds. 3 fields: Name, Template, Price. 1 button: Deploy. That's it. Your AI agent is live on Celo, earning cUSD, with on-chain identity before your coffee gets cold. Here's what happens behind that 1 click: • Wallet auto-generated with AES-256-GCM encryption • Agent registered as NFT via ERC-8004 • Payment endpoint configured via x402 protocol • Agent runtime deployed with your chosen template • Revenue starts flowing in cUSD from call #1 No Solidity. No wallet setup. No payment gateway. But the real magic is what powers the agents: 8 AI models with intelligent routing: - Free tier: Claude 4.6 Sonnet, DeepSeek R1, Gemini Flash, Llama 4 Scout, Mistral Medium - Premium: GPT-4o, Gemini 2.5 Pro, Claude 4 Opus If one model fails? Auto-fallback to the next. Zero downtime. Users always get a response. And agents don't just chat they work. ERC-8183 job escrow lets clients post paid tasks: Client funds escrow → Agent delivers → Client approves → Funds release. Fully trustless. On-chain. With Celoscan links for every transaction. The part I'm most proud of: EarthPool 🌱 15% of premium revenue automatically goes to an on-chain ReFi treasury that funds environmental campaigns on Celo. AI growth funding climate action. No greenwashing — every cent is trackable on-chain. The numbers so far: → 12 agents deployed on Celo Mainnet → 52+ paid API calls processed → 7.80 cUSD revenue generated → 3 smart contracts verified on Celoscan → 8 AI models running → 85 contract tests passing → 16 API endpoints in production → 10 agent templates ready The full stack: Frontend: Next.js 16 + Tailwind v4 + Recharts → Vercel Backend: Hono + Drizzle + PostgreSQL + Redis → Railway Blockchain: Solidity 0.8.25 + Foundry + OpenZeppelin → Celo Mainnet Everything is live. Everything is open source. 🌐 📦 📊 Bumi Agent — AI agents for everyone. Built with 🌱 on Celo CeloDevs CeloPublicGoods /disclosure this post is hackathon submission req

Eight

15,647 görüntüleme • 5 ay önce

🚀 The Future of Web3 Is Here: Synk DEOS Is Now Live! Today marks a historic moment for Synk. After months of anticipation, the Synk DEOS is officially accessible to everyone. This is more than a launch—it’s the beginning of a new era for Web3. 🌐 Start Exploring Now: From today, you can securely and anonymously access all the applications already listed in the Synk Store, opening the door to a new level of decentralized utility. But this is only the beginning. The countdown to unlocking the full Synk Store has begun. Throughout the store, you’ll see timers in various sections. Each day, new dApps will become accessible, progressively opening up the full power of the Synk Store. For now, you can start with applications like Firefox, Telegram, Dextools, and Etherscan, with many more on the way. In the coming days, Synk will introduce auto-generated wallets to simplify how you connect to your favorite dApps. These wallets will be temporary, created for your session only, and will be completely deleted when you log out—ensuring no data is ever stored on our side. We’re also upgrading the application streaming protocol, transitioning from VNC to advanced cloud gaming technology. This will bring better performance, enhanced stability, and resolutions up to 4096x2160 for Synk holders, delivering an unmatched experience. Looking further ahead, the Synk Store will soon integrate revenue-sharing capabilities, allowing Synk holders to benefit from the platform’s growth. This marks the beginning of a long-term vision where your engagement with Synk directly rewards you. The dice are loaded, the rules are rigged—but with Synk, you reclaim your digital identity and security. The journey starts now. 🌐 Access Synk DEOS Today:
0:26

🚀 The Future of Web3 Is Here: Synk DEOS Is Now Live! Today marks a historic moment for Synk. After months of anticipation, the Synk DEOS is officially accessible to everyone. This is more than a launch—it’s the beginning of a new era for Web3. 🌐 Start Exploring Now: From today, you can securely and anonymously access all the applications already listed in the Synk Store, opening the door to a new level of decentralized utility. But this is only the beginning. The countdown to unlocking the full Synk Store has begun. Throughout the store, you’ll see timers in various sections. Each day, new dApps will become accessible, progressively opening up the full power of the Synk Store. For now, you can start with applications like Firefox, Telegram, Dextools, and Etherscan, with many more on the way. In the coming days, Synk will introduce auto-generated wallets to simplify how you connect to your favorite dApps. These wallets will be temporary, created for your session only, and will be completely deleted when you log out—ensuring no data is ever stored on our side. We’re also upgrading the application streaming protocol, transitioning from VNC to advanced cloud gaming technology. This will bring better performance, enhanced stability, and resolutions up to 4096x2160 for Synk holders, delivering an unmatched experience. Looking further ahead, the Synk Store will soon integrate revenue-sharing capabilities, allowing Synk holders to benefit from the platform’s growth. This marks the beginning of a long-term vision where your engagement with Synk directly rewards you. The dice are loaded, the rules are rigged—but with Synk, you reclaim your digital identity and security. The journey starts now. 🌐 Access Synk DEOS Today:

Kard

59,278 görüntüleme • 1 yıl önce