Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Onyx just hit #1 on GitHub trending. Open source AI platform — self-hostable, works with every major LLM provider, and ships with: - Agentic RAG - Deep research mode - Custom agents - Web search - Code execution - Voice mode - Image generation - 50+ connectors out of... show more

0xMarioNawfal

254,717 subscribers

75,559 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

YOUR AI SECOND BRAIN IS NOW OPEN SOURCE. khoj-ai just hit 36,000 stars on GitHub / For a solo founder, one agent replaces an entire corporate knowledge system. Connect your docs, PDFs, Obsidian notes, Notion pages. Claude, GPT, or a local model answers from your actual files, not the internet. > Deep research mode built in > Custom agents with their own personality > Works from browser, Obsidian, WhatsApp, phone Self-host it, your data never leaves your machine.

YOUR AI SECOND BRAIN IS NOW OPEN SOURCE. khoj-ai just hit 36,000 stars on GitHub / For a solo founder, one agent replaces an entire corporate knowledge system. Connect your docs, PDFs, Obsidian notes, Notion pages. Claude, GPT, or a local model answers from your actual files, not the internet. > Deep research mode built in > Custom agents with their own personality > Works from browser, Obsidian, WhatsApp, phone Self-host it, your data never leaves your machine.

Defileo🔮

14,416 views • 1 month ago

Someone built a free and better alternative to Claude that runs 100% locally. → works with any LLM (Claude, GPT, Gemini, vLLM) → beats it on deep research → has Cowork-like capabilities → 50+ connectors out of the box → deploy in literally one command 100% open source. MIT license. 28k stars.

Someone built a free and better alternative to Claude that runs 100% locally. → works with any LLM (Claude, GPT, Gemini, vLLM) → beats it on deep research → has Cowork-like capabilities → 50+ connectors out of the box → deploy in literally one command 100% open source. MIT license. 28k stars.

How To Prompt

39,414 views • 4 months ago

Notion 3.4 is a big one! New building blocks. New AI. A lot shipped recently. Here’s what's new: → Dashboard view → Image generation → Presentation mode → AI skills → Tabs block → H4 headers → Archive pages → Voice dictation → Salesforce + Box connectors → Private Slack channels with agents → n8n MCP integration → …and more.

Notion 3.4 is a big one! New building blocks. New AI. A lot shipped recently. Here’s what's new: → Dashboard view → Image generation → Presentation mode → AI skills → Tabs block → H4 headers → Archive pages → Voice dictation → Salesforce + Box connectors → Private Slack channels with agents → n8n MCP integration → …and more.

Notion

231,550 views • 5 months ago

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

481,300 views • 3 months ago

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,982 views • 5 months ago

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere Unsloth Desktop is now available on and GitHub. GitHub: Blog and Guide:

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere Unsloth Desktop is now available on and GitHub. GitHub: Blog and Guide:

Unsloth AI

808,713 views • 28 days ago

Anthropic senior engineer just dropped a 1-hour course on building self-learning agentic systems with loops & graphs: • 00:19 - how Claude Code actually works • 14:20 - long horizon agents CLAUDE.md & Plan mode • 23:38 - Claude "skills" design patterns for agents • 44:01 - building agents & subagents with Claude • 59:34 - self-improving loops & graphs for Claude agents This 1-hour watch will replace a $500 agentic engineering course Watch today, then read how to build self-improving agents with "loops" and "graphs" in the article below

Anthropic senior engineer just dropped a 1-hour course on building self-learning agentic systems with loops & graphs: • 00:19 - how Claude Code actually works • 14:20 - long horizon agents CLAUDE.md & Plan mode • 23:38 - Claude "skills" design patterns for agents • 44:01 - building agents & subagents with Claude • 59:34 - self-improving loops & graphs for Claude agents This 1-hour watch will replace a $500 agentic engineering course Watch today, then read how to build self-improving agents with "loops" and "graphs" in the article below

Codez

66,404 views • 3 days ago

Today, we’re excited to announce the general availability of the Contextual AI Platform. This is the first enterprise platform designed for building specialized RAG agents to support expert knowledge work. What is a specialized RAG agent? First, a general-purpose AI agent is one designed to automate simple daily tasks like scheduling a meeting or responding to an email. On the other hand, a specialized RAG agent is one designed to augment subject-matter experts performing complex domain-specific work. The Contextual AI Platform allows you to create these agents easily and achieve SOTA accuracy right out of the box. Check out what the Contextual AI Platform can do.

Today, we’re excited to announce the general availability of the Contextual AI Platform. This is the first enterprise platform designed for building specialized RAG agents to support expert knowledge work. What is a specialized RAG agent? First, a general-purpose AI agent is one designed to automate simple daily tasks like scheduling a meeting or responding to an email. On the other hand, a specialized RAG agent is one designed to augment subject-matter experts performing complex domain-specific work. The Contextual AI Platform allows you to create these agents easily and achieve SOTA accuracy right out of the box. Check out what the Contextual AI Platform can do.

Contextual AI

879,586 views • 1 year ago

Thrilled to see Amazon Web Services making a major contribution to the open source AI community with the launch of the Strands Agents, an open source AI agents SDK! The core of Strands is the simple agentic loop that connects the model and tools together, like the two strands of DNA. This model-driven approach to agent building eliminates the need for complex agent orchestration by embracing the capabilities of state-of-the-art models to plan, chain thoughts, call tools, and reflect. Providing open source tools and interoperability with open source protocols is an important part of our strategy to enable an agentic future. Can't wait to see what you build with Strands!

Thrilled to see Amazon Web Services making a major contribution to the open source AI community with the launch of the Strands Agents, an open source AI agents SDK! The core of Strands is the simple agentic loop that connects the model and tools together, like the two strands of DNA. This model-driven approach to agent building eliminates the need for complex agent orchestration by embracing the capabilities of state-of-the-art models to plan, chain thoughts, call tools, and reflect. Providing open source tools and interoperability with open source protocols is an important part of our strategy to enable an agentic future. Can't wait to see what you build with Strands!

Swami Sivasubramanian

32,185 views • 1 year ago

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Santiago

73,062 views • 10 months ago

NVIDIA just dropped a 2.5-hour course on how to build coding agents, featuring the CTO of Cursor: 00:07 – self-driving codebases with async agents 37:50 – agentic AI, from the ground up 1:16:35 – context engineering for high-signal AI code reviews 1:53:26 – teach AI to code in any language Worth more than any $500 enterprise-AI course. Bookmark this & steal my harness, below.

NVIDIA just dropped a 2.5-hour course on how to build coding agents, featuring the CTO of Cursor: 00:07 – self-driving codebases with async agents 37:50 – agentic AI, from the ground up 1:16:35 – context engineering for high-signal AI code reviews 1:53:26 – teach AI to code in any language Worth more than any $500 enterprise-AI course. Bookmark this & steal my harness, below.

Phosphen

11,226 views • 2 months ago

Jane Street pays quants $500K+ to build what Nous Research just open-sourced for free. Hermes Agent - open-source, self-hosted, deploys in 30 minutes on a $5/month VPS. Kelly Criterion sizing, Expected Value scoring, 3 forecast sources across 20 cities, self-calibrating, TG alerts. All out of the box. No code required. Algorithms like these generate $100,000–$150,000 per quarter Wallet proof: This trader turned $300 into $123K trading weather. Every trade verifiable on-chain, every PnL public. The "retail can't compete with institutions" narrative is dead. You just need a terminal for copy every trade of such agents, i'm use this one:

Jane Street pays quants $500K+ to build what Nous Research just open-sourced for free. Hermes Agent - open-source, self-hosted, deploys in 30 minutes on a $5/month VPS. Kelly Criterion sizing, Expected Value scoring, 3 forecast sources across 20 cities, self-calibrating, TG alerts. All out of the box. No code required. Algorithms like these generate $100,000–$150,000 per quarter Wallet proof: This trader turned $300 into $123K trading weather. Every trade verifiable on-chain, every PnL public. The "retail can't compete with institutions" narrative is dead. You just need a terminal for copy every trade of such agents, i'm use this one:

cvxv666

276,617 views • 4 months ago

The real power of AI agents is collaboration. Box CTO Ben Kus joins LangChain CEO Harrison Chase to discuss what the future looks like when AI systems can work more like teammates than just assistants. Timestamps: 00:52 - Harrison's path to starting LangChain 01:54 - The different definitions of AI agents 03:16 - How agentic systems differ from traditional automation 06:20 - The evolution of AI agents 13:06 - The impact of deep research 17:22 - Deep agent capabilities and benefits 22:16 - How to recognize different modes 25:25 - The future of evaluation

The real power of AI agents is collaboration. Box CTO Ben Kus joins LangChain CEO Harrison Chase to discuss what the future looks like when AI systems can work more like teammates than just assistants. Timestamps: 00:52 - Harrison's path to starting LangChain 01:54 - The different definitions of AI agents 03:16 - How agentic systems differ from traditional automation 06:20 - The evolution of AI agents 13:06 - The impact of deep research 17:22 - Deep agent capabilities and benefits 22:16 - How to recognize different modes 25:25 - The future of evaluation

Box

54,980 views • 9 months ago

Here is what openai's new voice mode looks like with RAG. This lets you connect the voice agent to external sources to like company files, a website or a database. The world of customer support just changed forever Check it out

Here is what openai's new voice mode looks like with RAG. This lets you connect the voice agent to external sources to like company files, a website or a database. The world of customer support just changed forever Check it out

Yasser

300,407 views • 1 year ago

MAJOR DEPLOYMENT: AI Search Engine - Day Mode Officially Released ⚡️ After months of development and countless refinement hours, Day Mode for the Spectre AI Search Engine has landed. Every detail of the UI has been engineered with precision - a balanced white, black, and purple palette that elevates usability and makes the Search Engine cleaner, faster, and more accessible to every type of market participant. This release is more than design - it’s part of our broader infrastructure mission: building a professional-grade platform where crypto and DeFi research can be done with the speed, accuracy, and polish that serious investors demand. Experience the new Day/Dark toggle directly in the header: And this is just the beginning - much more is coming. #ai #web3 #innovation $SPECT

MAJOR DEPLOYMENT: AI Search Engine - Day Mode Officially Released ⚡️ After months of development and countless refinement hours, Day Mode for the Spectre AI Search Engine has landed. Every detail of the UI has been engineered with precision - a balanced white, black, and purple palette that elevates usability and makes the Search Engine cleaner, faster, and more accessible to every type of market participant. This release is more than design - it’s part of our broader infrastructure mission: building a professional-grade platform where crypto and DeFi research can be done with the speed, accuracy, and polish that serious investors demand. Experience the new Day/Dark toggle directly in the header: And this is just the beginning - much more is coming. #ai #web3 #innovation $SPECT

SPECTRE AI

13,914 views • 1 year ago

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

Vikas gupta

18,053 views • 3 days ago