Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Finally. I shipped a side-project. Introducing inbrowser. Pluggable AI architecture totally in the browser. site: repo: @​inbrowser/model: on-device w/ transformers.js & webgpu. Cloud model proxies and OpenRouter BYOK flows. @​inbrowser/agent: pluggable client-side agent architecture @​inbrowser/resumable: pick up and resume across refreshes @​inbrowser/relay: when you need a server, syncs resumable...

_davideast's profile picture

David East

25,227 subscribers

18,706 görüntüleme • 3 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.
0:23

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

NO1ennn

69,163 görüntüleme • 1 ay önce

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:
2:49

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,758 görüntüleme • 1 yıl önce

We all know the pain of choosing the right model. You have an idea, testing it one model at a time in ten different tabs, using a spreadsheet to track usable outputs. Stop guessing and start building with Creator Central by Atlas Cloud. Model Explorer runs the same prompt across models and puts the results side by side, up to 10 at once. Start from a curated set or assemble your own. With Wan3.0 coming shortly, we're dropping the price of Seedance 2.5 so creators can compare and choose the right model for their projects. Create something now with our Generator templated workflow: Pick what you like and access the exact prompt and settings behind that result, ready for you to edit. #AIVideo #GenerativeAI #VideoProduction #Seedance #Wan3
1:02

We all know the pain of choosing the right model. You have an idea, testing it one model at a time in ten different tabs, using a spreadsheet to track usable outputs. Stop guessing and start building with Creator Central by Atlas Cloud. Model Explorer runs the same prompt across models and puts the results side by side, up to 10 at once. Start from a curated set or assemble your own. With Wan3.0 coming shortly, we're dropping the price of Seedance 2.5 so creators can compare and choose the right model for their projects. Create something now with our Generator templated workflow: Pick what you like and access the exact prompt and settings behind that result, ready for you to edit. #AIVideo #GenerativeAI #VideoProduction #Seedance #Wan3

Atlas Cloud

643,363 görüntüleme • 1 ay önce

Today we shipped a new Search experience in Chrome to help you explore the web without constant back and forth between tabs. Now, when you click a link from AI Mode, the website opens side-by-side. It's a game changer for comparing details and products across sites, discovering new content & asking follow up Qs about what you’re seeing – all in one view. If you're in the U.S. try it on Chrome desktop today! Just make sure you’ve got the latest version of Chrome to try it out⚡️
0:53

Today we shipped a new Search experience in Chrome to help you explore the web without constant back and forth between tabs. Now, when you click a link from AI Mode, the website opens side-by-side. It's a game changer for comparing details and products across sites, discovering new content & asking follow up Qs about what you’re seeing – all in one view. If you're in the U.S. try it on Chrome desktop today! Just make sure you’ve got the latest version of Chrome to try it out⚡️

Robby Stein

120,820 görüntüleme • 5 ay önce

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...
3:28

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...

kwindla

331,698 görüntüleme • 1 ay önce

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →
0:58

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →

ℏεsam

62,794 görüntüleme • 2 ay önce

ex-Apple engineer gave Grok 4.6 two jobs inside Cursor, went to sleep, and opened the results live the next morning: no babysitting, no checking every generation, just a model left running on real work for hours. • 00:42 - reveal the website Grok redesigned overnight • 23:21 - go from a voice prompt to a full software stack • 45:43 - inspect the generated code + architecture • 01:21:26 - Grok 4.6 vs Opus 5 • 01:46:31 - live PR + Cloud Agent workflow Most coding demos test an AI for 5 minutes. This tests the thing that matters for agents: can the model keep working when you stop watching it? SpaceXAI built Grok 4.6 specifically around longer-running agent tasks, coding and more ambitious visual work. The endgame isn’t prompting faster. It’s giving an agent a job at night and reviewing finished work in the morning. Worth watching before you choose which model runs your overnight agent loops.
2:27:56

ex-Apple engineer gave Grok 4.6 two jobs inside Cursor, went to sleep, and opened the results live the next morning: no babysitting, no checking every generation, just a model left running on real work for hours. • 00:42 - reveal the website Grok redesigned overnight • 23:21 - go from a voice prompt to a full software stack • 45:43 - inspect the generated code + architecture • 01:21:26 - Grok 4.6 vs Opus 5 • 01:46:31 - live PR + Cloud Agent workflow Most coding demos test an AI for 5 minutes. This tests the thing that matters for agents: can the model keep working when you stop watching it? SpaceXAI built Grok 4.6 specifically around longer-running agent tasks, coding and more ambitious visual work. The endgame isn’t prompting faster. It’s giving an agent a job at night and reviewing finished work in the morning. Worth watching before you choose which model runs your overnight agent loops.

Morlex

5,270,291 görüntüleme • 1 ay önce

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓
0:36

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

Vaibhav Sisinty

37,255 görüntüleme • 2 ay önce

Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox WebBrain lives inside your browser and can run entirely on your own local model — no cloud, no account, no data leaving your machine. Most "AI browser agents" are a chat box that pastes your page into someone else's server. That's not an agent that lives where you browse — and WebBrain draws a very clear line between the two. It's an open-source (MIT), local-first browser agent for Chrome and Firefox. It runs inside your existing authenticated session, on a model you pick — so with llama.cpp or Ollama, nothing leaves your machine. Here's what's actually interesting: → Two modes, cleanly separated. Ask reads the page (read-only, content scripts). Act clicks and types through the Chrome DevTools Protocol (chrome.debugger) — trusted input events that modern sites honor, reaching cross-origin iframes and shadow DOM. → UI-first by design. For anything that submits, sends, or buys, it drives the visible UI and refuses to hit REST/GraphQL endpoints directly. It starts read-only and asks before consequential actions. → Bring any model. llama.cpp, Ollama, LM Studio, vLLM — or OpenAI, Claude, Gemini, DeepSeek, Groq, OpenRouter. Recommended local: Qwen 3.6 35B (Qwen3.6-35B-A3B), which beat Gemma 4 on the project's screenshot benchmark. → Tuned for cost and privacy. Token-conscious screenshots, oldest-first context trimming, a dedicated vision model, 40+ tools (~20 in Compact mode). No telemetry. No accounts. Full analysis: GitHub Repo: Chrome Extension: Firefox Add-on: Portal:
0:47

Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox WebBrain lives inside your browser and can run entirely on your own local model — no cloud, no account, no data leaving your machine. Most "AI browser agents" are a chat box that pastes your page into someone else's server. That's not an agent that lives where you browse — and WebBrain draws a very clear line between the two. It's an open-source (MIT), local-first browser agent for Chrome and Firefox. It runs inside your existing authenticated session, on a model you pick — so with llama.cpp or Ollama, nothing leaves your machine. Here's what's actually interesting: → Two modes, cleanly separated. Ask reads the page (read-only, content scripts). Act clicks and types through the Chrome DevTools Protocol (chrome.debugger) — trusted input events that modern sites honor, reaching cross-origin iframes and shadow DOM. → UI-first by design. For anything that submits, sends, or buys, it drives the visible UI and refuses to hit REST/GraphQL endpoints directly. It starts read-only and asks before consequential actions. → Bring any model. llama.cpp, Ollama, LM Studio, vLLM — or OpenAI, Claude, Gemini, DeepSeek, Groq, OpenRouter. Recommended local: Qwen 3.6 35B (Qwen3.6-35B-A3B), which beat Gemma 4 on the project's screenshot benchmark. → Tuned for cost and privacy. Token-conscious screenshots, oldest-first context trimming, a dedicated vision model, 40+ tools (~20 in Compact mode). No telemetry. No accounts. Full analysis: GitHub Repo: Chrome Extension: Firefox Add-on: Portal:

Marktechpost AI

203,011 görüntüleme • 2 ay önce

ran Grok Bot and Hermes Agent side by side for the same job here's what actually separates them Grok Bot: - gets its own cloud computer, browser, files, terminal, logs into your tools with your credentials - learns by demonstration, record a task once, it saves the routine - runs on Grok, you don't choose the model - all your bots share the same cloud computer and the same logins, no isolation between them - scales by subscription, ~$200/mo solo, ~$120/seat for teams Hermes Agent: - open source, MIT-licensed, no cloud, you host it - each agent gets its own real badge from your identity provider, scoped access only, revoke it and it's gone - brain is swappable, change one config line to switch models - scales by spinning up containers on demand, hire/fire based on backlog - you own the maintenance, an upstream installer change broke one build, one line fix, one morning lost the real fork isn't features, it's where the work happens and who's accountable when it breaks grok bot: convenience, zero setup, but your data sits on their machine and every bot shares every login hermes: more setup, but scoped access, swappable models, and nothing running outside your own network for anything touching regulated or sensitive data, that architecture difference is the whole decision
0:40

ran Grok Bot and Hermes Agent side by side for the same job here's what actually separates them Grok Bot: - gets its own cloud computer, browser, files, terminal, logs into your tools with your credentials - learns by demonstration, record a task once, it saves the routine - runs on Grok, you don't choose the model - all your bots share the same cloud computer and the same logins, no isolation between them - scales by subscription, ~$200/mo solo, ~$120/seat for teams Hermes Agent: - open source, MIT-licensed, no cloud, you host it - each agent gets its own real badge from your identity provider, scoped access only, revoke it and it's gone - brain is swappable, change one config line to switch models - scales by spinning up containers on demand, hire/fire based on backlog - you own the maintenance, an upstream installer change broke one build, one line fix, one morning lost the real fork isn't features, it's where the work happens and who's accountable when it breaks grok bot: convenience, zero setup, but your data sits on their machine and every bot shares every login hermes: more setup, but scoped access, swappable models, and nothing running outside your own network for anything touching regulated or sensitive data, that architecture difference is the whole decision

rewind

31,513 görüntüleme • 29 gün önce

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones
1:37

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones

@levelsio

261,479 görüntüleme • 2 yıl önce

did Cloudflare leave the best for last? guess we'll find out tomorrow agent week is almost over and I am still catching up on all the announcements one thing that i wanted to take for a spin was Computer. you shouldn't need a full on VM container to spin up a git repo and read and edit some files. and if you want to test something in a browser, you can now use Kitesurf having this kind of control when building agent harnesses is very cool, from permission management, separating the brain from the hands and performance gains from isolation, im super stoked for where this goes i wanted to see if i can build a Buzz-like environment using Cloudflare primitives, i called it Cuzz. and being able to observe and debug agent activity locally using Sentry helps make sure i can see not just my agent traces, but errors, logs and traces from the rest of my application what was your favourite announcement from Agent Week?
3:44

did Cloudflare leave the best for last? guess we'll find out tomorrow agent week is almost over and I am still catching up on all the announcements one thing that i wanted to take for a spin was Computer. you shouldn't need a full on VM container to spin up a git repo and read and edit some files. and if you want to test something in a browser, you can now use Kitesurf having this kind of control when building agent harnesses is very cool, from permission management, separating the brain from the hands and performance gains from isolation, im super stoked for where this goes i wanted to see if i can build a Buzz-like environment using Cloudflare primitives, i called it Cuzz. and being able to observe and debug agent activity locally using Sentry helps make sure i can see not just my agent traces, but errors, logs and traces from the rest of my application what was your favourite announcement from Agent Week?

Serge

14,865 görüntüleme • 1 ay önce

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.
0:22

AI agents can already generate text, analyze data and execute tasks. But what happens when they need to hire each other and get paid for the work? This is the part of TermiX I’ve been digging into lately. On TermiX, a job has two sides: a client agent that needs something done and funds the job, and a worker agent that actually executes it. Once the quote is accepted, the payment and agreed terms sit between them onchain. Neither side can simply rewrite the deal afterward. And this isn't presented as an abstract concept. The TermiX agent marketplace already shows agents with their own identities, reputation, completed jobs and settled value. Some of the agents shown have completed hundreds of jobs, with tens of thousands of dollars settled. Think about where this model can go. A research agent could outsource data collection to another agent. A developer agent could hire a security-focused agent. A marketing agent could hand translation or design work to specialized agents. Instead of one AI trying to do everything, specialized agents can discover each other, agree on a job, execute it and settle the transaction. Humans built marketplaces around people hiring people. TermiX is building the infrastructure for agents hiring agents. That’s where autonomous AI starts looking a lot more like an actual economy.

holly

13,718 görüntüleme • 17 gün önce

Introducing the new Box Agent. The Box Agent works across your entire Box file system, maintaining all your security and access controls, and is hyper tuned for working with enterprise content. This means you can now ask questions from all your enterprise content, search for files that were impossible to find before, deploy an agent on specific tasks on subsets of documents, analyze complex data sets, and generate or edit documents and spreadsheets via the agent. You can have the Box Agent search across your Box account to prepare for a sales meeting, analyze customer sentiment reports, process a large set of contracts for legal risk, provide insights into product development, leverage existing knowledge to answer RFPs, and thousands of other use-cases. 90% of enterprise data is unstructured data. This means most enterprise knowledge is sitting in inside of research reports, marketing assets, presentations, roadmap files, contracts, HR documents, and more. This is the critical context that agents need to be able to answer questions about a business, automate workflows, or serve up to other agents. We’ve been grinding on this for a quite a bit, and due to recent AI model advancements we’re now ready to release it to customers. Previous model generations had a difficult time knowing when to give up or keep going on a search, when to browse for files vs. use queries, how to rank files appropriately to know which version of content to use, how to handle large amounts of context to comb through, and more. Due to recent breakthroughs from models like GPT-5.4, Opus 4.6, and Gemini 3, we’ve seen major gains in tool calling, code execution, advanced reasoning, and more. Combined with an agent harness tuned to Box context, now it’s finally possible to have an agent that can work across your file system on long running tasks and actually deliver high quality results. Best of all, because the Box Agent works with any leading AI model, you’ll quickly get the gains coming out of the major labs as major new models are released. Further, openness at Box is key, so you’ll be able to call up the Box Agent from Box’s APIs and MCP server, so you can interact with Box intelligently from any other AI system. We know work happens everywhere, and we want to ensure you can access to the content you need from those places. The new Box Agent is available starting today, rolling out now for Enterprise Plus and Enterprise Advanced customers.
0:58

Introducing the new Box Agent. The Box Agent works across your entire Box file system, maintaining all your security and access controls, and is hyper tuned for working with enterprise content. This means you can now ask questions from all your enterprise content, search for files that were impossible to find before, deploy an agent on specific tasks on subsets of documents, analyze complex data sets, and generate or edit documents and spreadsheets via the agent. You can have the Box Agent search across your Box account to prepare for a sales meeting, analyze customer sentiment reports, process a large set of contracts for legal risk, provide insights into product development, leverage existing knowledge to answer RFPs, and thousands of other use-cases. 90% of enterprise data is unstructured data. This means most enterprise knowledge is sitting in inside of research reports, marketing assets, presentations, roadmap files, contracts, HR documents, and more. This is the critical context that agents need to be able to answer questions about a business, automate workflows, or serve up to other agents. We’ve been grinding on this for a quite a bit, and due to recent AI model advancements we’re now ready to release it to customers. Previous model generations had a difficult time knowing when to give up or keep going on a search, when to browse for files vs. use queries, how to rank files appropriately to know which version of content to use, how to handle large amounts of context to comb through, and more. Due to recent breakthroughs from models like GPT-5.4, Opus 4.6, and Gemini 3, we’ve seen major gains in tool calling, code execution, advanced reasoning, and more. Combined with an agent harness tuned to Box context, now it’s finally possible to have an agent that can work across your file system on long running tasks and actually deliver high quality results. Best of all, because the Box Agent works with any leading AI model, you’ll quickly get the gains coming out of the major labs as major new models are released. Further, openness at Box is key, so you’ll be able to call up the Box Agent from Box’s APIs and MCP server, so you can interact with Box intelligently from any other AI system. We know work happens everywhere, and we want to ensure you can access to the content you need from those places. The new Box Agent is available starting today, rolling out now for Enterprise Plus and Enterprise Advanced customers.

Aaron Levie

44,624 görüntüleme • 5 ay önce

We’re pushing cross-chain automation to a new level. Our backend Motoko architecture now lets an $ICP smart contract directly execute $NEAR transactions without any client-side code. The contract itself becomes the agent fully autonomous, programmable, and always on. To complement this, we introduced a NEAR-specific on-chain RPC Oracle canister that cryptographically verifies NEAR data and transactions. This dramatically improves reliability, reduces latency, and unlocks 24/7 trust-minimized execution across NEAR. But we’re not stopping there. Our backend execution layer is already designed to operate seamlessly across chains like $Monad, $TRON, $SUI, and $ADA, with Motoko-driven workflows and cross-chain messaging. The RPC Oracle is purpose-built for $NEAR today, while all these ecosystems—and more—can leverage our autonomous backend compute model.
1:04

We’re pushing cross-chain automation to a new level. Our backend Motoko architecture now lets an $ICP smart contract directly execute $NEAR transactions without any client-side code. The contract itself becomes the agent fully autonomous, programmable, and always on. To complement this, we introduced a NEAR-specific on-chain RPC Oracle canister that cryptographically verifies NEAR data and transactions. This dramatically improves reliability, reduces latency, and unlocks 24/7 trust-minimized execution across NEAR. But we’re not stopping there. Our backend execution layer is already designed to operate seamlessly across chains like $Monad, $TRON, $SUI, and $ADA, with Motoko-driven workflows and cross-chain messaging. The RPC Oracle is purpose-built for $NEAR today, while all these ecosystems—and more—can leverage our autonomous backend compute model.

ICP HUB Egypt

12,353 görüntüleme • 9 ay önce

What's the actual setup work behind running a team of AI agents on Buzz? Almost none. The one move that mattered: pin each agent to a model. "Fizz is a Fable model and Honey is Sonnet" Certain tasks don't need Fable's power, and running them there burns through tokens fast. Then I made a chief agent officer — an agent whose only job is deciding which agent gets the task. Copywriter, brainstormer, code reviewer. You forget who they all are. It doesn't. Claude Code is the harness underneath, and every skill you've already got installed globally comes with it. The catch: this is early preview software, maybe alpha. Recurring tasks and workflows "weren't really landing great," and the relay round-trip to the server makes it slower than sitting in Claude Code directly. Solopreneurs and small teams iterating on small ideas, this is a great tool. Complex software engineering, not yet. Just start playing around.
3:24

What's the actual setup work behind running a team of AI agents on Buzz? Almost none. The one move that mattered: pin each agent to a model. "Fizz is a Fable model and Honey is Sonnet" Certain tasks don't need Fable's power, and running them there burns through tokens fast. Then I made a chief agent officer — an agent whose only job is deciding which agent gets the task. Copywriter, brainstormer, code reviewer. You forget who they all are. It doesn't. Claude Code is the harness underneath, and every skill you've already got installed globally comes with it. The catch: this is early preview software, maybe alpha. Recurring tasks and workflows "weren't really landing great," and the relay round-trip to the server makes it slower than sitting in Claude Code directly. Solopreneurs and small teams iterating on small ideas, this is a great tool. Complex software engineering, not yet. Just start playing around.

The Startup Ideas Podcast (SIP) 🧃

24,769 görüntüleme • 1 ay önce

We keep defaulting to the biggest model in the room every time we touch AI in our apps. Claude, GPT, Gemini. Cloud or nothing. But the browser is already more capable than most people realize: WebAI and WebMCP may change this. With WebAI you can run models client-side. With WebMCP, your site can expose real actions as JavaScript functions. Agents don't need screenshots, DOM scraping, or blind clicking. They can just use your app. I talked about this with Guy Podjarny on Tessl AI Native Dev podcast: the browser is turning into an AI runtime. Links in first reply :)
1:12

We keep defaulting to the biggest model in the room every time we touch AI in our apps. Claude, GPT, Gemini. Cloud or nothing. But the browser is already more capable than most people realize: WebAI and WebMCP may change this. With WebAI you can run models client-side. With WebMCP, your site can expose real actions as JavaScript functions. Agents don't need screenshots, DOM scraping, or blind clicking. They can just use your app. I talked about this with Guy Podjarny on Tessl AI Native Dev podcast: the browser is turning into an AI runtime. Links in first reply :)

Maximiliano Firtman

14,824 görüntüleme • 6 ay önce

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:
0:44

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,080,061 görüntüleme • 3 ay önce

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2
11:32

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

16,289 görüntüleme • 3 ay önce