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.

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert.... It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential. OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose. rohit and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think! Try it out: (requires your own API key) Source code:show more

Andrew Ng

1,873,071 subscribers

1,159,470 views • 1 month ago •via X (Twitter)

Science & Technology Education Health & Wellness

Anya Rossi• Live Now

Private livecam show

34 Comments

Sahas Vivek1 month ago

how's this different from @openclaw or hermes by @NousResearch

E-Worker1 month ago

hmm, at least change the style a bit, do you have to copy us as is?

Dan McAteer1 month ago

Very cool. Any plans to allow auth through Codex/Claude Code?

Christian Catalini1 month ago

Own the weights of production!

Gregor Zunic1 month ago

We can help you add browser use ability!

Filecoin1 month ago

finished work belongs in durable, verifiable storage outside any single machine so it remains available after the laptop is gone

xp Ehsaan1 month ago

@grok how is this any different than Hermes agent ?

Shubham Saboo1 month ago

Love it Andrew and @rohitcprasad. Will be looking into it. Expect some PRs :)

Ben Despain1 month ago

Why isn't Grok included? Seems like a glaring omission...

Rohith1 month ago

Who will pay the bills. get OpenCompany:

Ornith1 month ago

🫡

Augustinas Malinauskas1 month ago

Really nice, very similar to

John Connor1 month ago

bro why don't you cure cancer or something instead of building the same shit as everyone else.

Sid Sharma1 month ago

Would love to see @inception_ai models supported too. Mercury’s speed make it a good fit for this workflow.

JQ Lee1 month ago

Great @AndrewYNg ! How do you think about Agent client protocol! Will deep dive your project. Lately I’ve been implementing video editing agent team with ACP

Yousef Rol1 month ago

how does it differs from opencl... oh its andrew GL! will def try it out!

Gaetan Semet1 month ago

@grok how is that different from Copilot App ?

Latentum1 month ago

how is it different from openclaw/hermes?

Dishant Miyani1 month ago

wait isnt this just another hermes agent?

M01 month ago

can it make videos like this too?

AlloomiAI1 month ago

OpenLoomi already covers the full AI coworker stack—docs, messages, calendars and cross-app actions. We go further with self-evolving memory and a proactive Loop, so it learns from ongoing work and keeps working between prompts. We’re open source too—feedback, critique and contributions are welcome:

David Peterson1 month ago

> "OpenWorker runs on your Mac, with Windows support coming soon." And Linux?

Iuliia Petryshyn1 month ago

Thanks for promoting open! We are building with the same principles in mind - open source, fully self hostable, model agnostic agentic runtime!

Christie1 month ago

i believe perplexity is doing the same thing or no?

Mike Gannotti1 month ago

voice-controlled multi-agent orchestration is where this is all heading... we've been testing similar with our Hermes agent fleet. the real threshold is whether the agent finishes the job without you steering every stepvoice-controlled multi-agent orchestration is where this is all heading... we've been testing similar with our Hermes agent fleet. the real threshold is whether the agent finishes the job without you steering every step

VC Intern1 month ago

AI Suite made models portable. OpenWorker applies the same idea to the entire coworker:

John Treadway1 month ago

@peteskomoroch @openwork vs OpenWorker? I’m going to launch #OpenLoafer. Takes your money and barely gets anything done. $100/month per seat. Requires HR and lawyers to fire them. Union version is $200.

Rajat Gahlot1 month ago

How’s this different from the Hermes agent by @NousResearch ?

Dave Waring1 month ago

Thanks for doing this and for MIT license. Open Source FTW!

Artem1 month ago

bring your own key quietly unbundles the agent from the model bill. once people see the raw per task cost of finished work a lot of pricing pages stop making sense

Lukas rimkus1 month ago

Can we expect to have linux support any time soon ?

Daniel Lenton1 month ago

Nice! Does it support voice calls, live screen share and learning from demonstrations etc. like

Hemachandiran1 month ago

Really loved the privacy of the open router. Are there any plans to add more use cases?

AS Maruf 🇨🇦🇧🇩1 month ago

@grok is it similar to open claw and hermes agent?

Related Videos

🚨 THIS IS ACTUALLY INSANE 𝗔𝗻𝗱𝗿𝗲𝘄 𝗡𝗴 just open sourced a free AI coworker that delivers FINISHED work, not chat. the GitHub repo already has 16,000+ stars. It lets you: → say the outcome: "prepare the customer brief", "untangle my calendar" → watch it break the task into steps and work across your desktop, files, and apps → keep control: writes, sends, and shell commands are approval-gated → connect 25+ tools — GitHub, Slack, Jira, Notion, Gmail, Calendar — plus anything over MCP → run it on a schedule: morning brief, weekly report, standing watch no subscriptions. no model lock-in. bring your own key — OpenAI, Anthropic, Gemini, DeepSeek, Kimi, Grok — or run fully local with Ollama. your data leaves only through the model and integrations you choose. this is where one-person businesses are headed. save this for later.

🚨 THIS IS ACTUALLY INSANE 𝗔𝗻𝗱𝗿𝗲𝘄 𝗡𝗴 just open sourced a free AI coworker that delivers FINISHED work, not chat. the GitHub repo already has 16,000+ stars. It lets you: → say the outcome: "prepare the customer brief", "untangle my calendar" → watch it break the task into steps and work across your desktop, files, and apps → keep control: writes, sends, and shell commands are approval-gated → connect 25+ tools — GitHub, Slack, Jira, Notion, Gmail, Calendar — plus anything over MCP → run it on a schedule: morning brief, weekly report, standing watch no subscriptions. no model lock-in. bring your own key — OpenAI, Anthropic, Gemini, DeepSeek, Kimi, Grok — or run fully local with Ollama. your data leaves only through the model and integrations you choose. this is where one-person businesses are headed. save this for later.

Vikas gupta

94,085 views • 15 days ago

What does it mean when an AI model is “open weights” and how is it different than “open source”? Welcome to the next episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! Every week we will discuss open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Episode 3 out next week; episode 1 linked below. Please leave all your questions about open-source & open-weight AI in the comments. This is a super important topic that is novel to most people, and it can be challenging to grasp - so your questions are shared with many others.

What does it mean when an AI model is “open weights” and how is it different than “open source”? Welcome to the next episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! Every week we will discuss open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Episode 3 out next week; episode 1 linked below. Please leave all your questions about open-source & open-weight AI in the comments. This is a super important topic that is novel to most people, and it can be challenging to grasp - so your questions are shared with many others.

Harper Carroll

32,624 views • 24 days ago

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

Bindu Reddy

2,572,380 views • 2 months ago

Slack just killed Buzz. One click to add your own open source NanoClaw agent to Slack. If you want more agents, just ask it. Collaborate with your agents in a shared room. Work together and tag them on a canvas. Slack is the new Slack.

Slack just killed Buzz. One click to add your own open source NanoClaw agent to Slack. If you want more agents, just ask it. Collaborate with your agents in a shared room. Work together and tag them on a canvas. Slack is the new Slack.

Gavriel Cohen

44,764 views • 21 days ago

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

Paul Couvert

41,245 views • 6 months ago

Mureka vs. Suno Suno might be a popular choice, but gives you way more control and creative flexibility. With Mureka, you can: • Use audio as a prompt, not just text • Keep the vocals consistent throughout your track • Train your own custom model • Access an open API to build or connect it with other tools

Mureka vs. Suno Suno might be a popular choice, but gives you way more control and creative flexibility. With Mureka, you can: • Use audio as a prompt, not just text • Keep the vocals consistent throughout your track • Train your own custom model • Access an open API to build or connect it with other tools

Nelly;

29,436 views • 1 year ago

Claude Fable 5 is back! GPT- 5.6 is coming soon! But how much do you trust your Al Agent or chatbot? Are you sure its performance aligns with your intentions? As of today iFixAi is available in Claude Code, Open AI Codex, Cursor and many more! And it is open-source! iFixAi is where Al red teaming meets Operational Assurance. It runs in auto, and in under 5 mins you can have a good idea if you can trust your Agent/chatbot. Key Features: 🕵️‍♂️ Setup Discovery Reads your agent's real configuration, its tools, rules, and permissions. 👷 Fixture Builder Turns that setup into a complete test. No YAML, no flags, no config to write. 🌐 Any Model, Any Provider Runs the 45 inspections on the model you actually ship. ⚖️ A Independent Grading Your agent is judged by a different vendor's model, never itself. No Al grading its own homework. 📊 Interactive Scorecard An A to F grade in minutes, with exactly what failed and why. Repo in the comments below 👇👇👇

Claude Fable 5 is back! GPT- 5.6 is coming soon! But how much do you trust your Al Agent or chatbot? Are you sure its performance aligns with your intentions? As of today iFixAi is available in Claude Code, Open AI Codex, Cursor and many more! And it is open-source! iFixAi is where Al red teaming meets Operational Assurance. It runs in auto, and in under 5 mins you can have a good idea if you can trust your Agent/chatbot. Key Features: 🕵️‍♂️ Setup Discovery Reads your agent's real configuration, its tools, rules, and permissions. 👷 Fixture Builder Turns that setup into a complete test. No YAML, no flags, no config to write. 🌐 Any Model, Any Provider Runs the 45 inspections on the model you actually ship. ⚖️ A Independent Grading Your agent is judged by a different vendor's model, never itself. No Al grading its own homework. 📊 Interactive Scorecard An A to F grade in minutes, with exactly what failed and why. Repo in the comments below 👇👇👇

Dimitris Neocleous

5,800,719 views • 2 months ago

The corporate system wants you trading time for a paycheck. The alternative is building automated leverage. You do not need a team of engineers. You just need the right open-source architecture. Here are 10 GitHub repos to automate your workflows, replace manual labor, and direct your own reality: 1. n8n Bypass expensive SaaS subscriptions. Build custom AI automation workflows that run on your own servers. 2. Ollama Stop sending your private data to massive API providers. Run heavy AI models locally on your own machine. Complete privacy. 3. Open Interpreter Let language models control your computer. Automate the repetitive corporate tasks they pay you to do manually. 4. Aider An AI pair programmer that lives in your terminal. Stop writing boilerplate code and focus strictly on the architecture. 5. Dify An open-source LLM app development platform. Build and deploy functional AI agents in minutes, not months. 6. Flowise A drag-and-drop UI to build customized LLM flows. You do not need to be a senior developer to build massive leverage. 7. Supabase Spin up a Postgres database, authentication, and instant APIs. Own your backend entirely. 8. Auto-GPT Give an AI an objective and let it execute. It browses the web, writes code, and chains thoughts together autonomously. 9. Outline An open-source knowledge base for your personal leverage. Stop losing your documentation in arbitrary corporate systems. 10. NocoDB Turn any database into a smart spreadsheet. Keep your data on your own infrastructure and stop paying for convenience. The secret to tech survival? Stop playing by their rules. Build your own systems and take your leverage with you.

The corporate system wants you trading time for a paycheck. The alternative is building automated leverage. You do not need a team of engineers. You just need the right open-source architecture. Here are 10 GitHub repos to automate your workflows, replace manual labor, and direct your own reality: 1. n8n Bypass expensive SaaS subscriptions. Build custom AI automation workflows that run on your own servers. 2. Ollama Stop sending your private data to massive API providers. Run heavy AI models locally on your own machine. Complete privacy. 3. Open Interpreter Let language models control your computer. Automate the repetitive corporate tasks they pay you to do manually. 4. Aider An AI pair programmer that lives in your terminal. Stop writing boilerplate code and focus strictly on the architecture. 5. Dify An open-source LLM app development platform. Build and deploy functional AI agents in minutes, not months. 6. Flowise A drag-and-drop UI to build customized LLM flows. You do not need to be a senior developer to build massive leverage. 7. Supabase Spin up a Postgres database, authentication, and instant APIs. Own your backend entirely. 8. Auto-GPT Give an AI an objective and let it execute. It browses the web, writes code, and chains thoughts together autonomously. 9. Outline An open-source knowledge base for your personal leverage. Stop losing your documentation in arbitrary corporate systems. 10. NocoDB Turn any database into a smart spreadsheet. Keep your data on your own infrastructure and stop paying for convenience. The secret to tech survival? Stop playing by their rules. Build your own systems and take your leverage with you.

Katyayani Shukla

16,964 views • 4 months ago

The open-source & open-weight frontier is 7 months behind the closed-model frontier. Let’s talk about it. Check out last week’s episode for the reasons why you might want to consider open-source & open-weight models. Welcome to the fourth episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! We have been discussing open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Please leave all your questions about open-source & open-weight AI in the comments! This is a super important topic that is novel to most people, and it can be challenging to grasp - so rest assured your questions are shared with many others!

The open-source & open-weight frontier is 7 months behind the closed-model frontier. Let’s talk about it. Check out last week’s episode for the reasons why you might want to consider open-source & open-weight models. Welcome to the fourth episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! We have been discussing open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Please leave all your questions about open-source & open-weight AI in the comments! This is a super important topic that is novel to most people, and it can be challenging to grasp - so rest assured your questions are shared with many others!

Harper Carroll

17,238 views • 10 days ago

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 views • 1 month ago

What is Clude Clone? It's a AI version of you that runs on your Mac. It learns how you write, think, and decide from your own screen, meetings, and apps, then drafts replies and answers questions as you. Runs locally. Your data stays on your device. You approve everything. It remembers. Clude quietly captures what you see and do, meetings, connected apps, your desktop, into a private memory that lives entirely on your Mac. Nothing is uploaded. It learns you. That memory gets distilled into a model of your voice, your relationships, and how you make decisions. It shows you what it's picked up, you confirm or correct it. It gets sharper every time. It acts as you. Ask it to reply as me, or ask your clone a question directly. It responds in your voice, grounded in what you actually know, always behind your approval. Powered by Hermes It stays yours. Local-first. Honestly labeled as an AI clone. Nothing leaves your device unless you opt in, and even then, only a distilled profile, never your raw data. Not a generic chatbot. Your actual voice, learned from your actual work.

seb

11,599 views • 2 months ago

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 views • 2 months ago

Want to build your own v0 or AI agent? Three open-source templates you should check out: 1. Have an AI create a deployment and users "claim" it 2. AI chatbot with code generation / execution 3. Slackbot with tool calling

Sensitive content

Want to build your own v0 or AI agent? Three open-source templates you should check out: 1. Have an AI create a deployment and users "claim" it 2. AI chatbot with code generation / execution 3. Slackbot with tool calling

Lee Robinson

51,030 views • 1 year ago

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

girish

460,844 views • 3 months ago

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.

Akshay 🚀

55,693 views • 9 days ago

Palantir CEO Alex Karp on why the model is not the moat. The application layer is: "To make them valuable in an enterprise, like a battlefield, regulated, or manufacturing context, you have to have what's called an application layer." "We have this thing called ontology that now everyone's copying. It takes a large language model and makes it safe and useful and precise." "Safe because it doesn't touch your underlying data." "Safe because it prevents the large language model from caching your data and replicating your business." The tell for any enterprise AI pitch: ask what sits between the model and your data. If the answer is nothing, you are not buying leverage. You are renting a fast way to hand your business to whoever owns the weights. Alex Karp, CEO of Palantir, on CNBC.

Palantir CEO Alex Karp on why the model is not the moat. The application layer is: "To make them valuable in an enterprise, like a battlefield, regulated, or manufacturing context, you have to have what's called an application layer." "We have this thing called ontology that now everyone's copying. It takes a large language model and makes it safe and useful and precise." "Safe because it doesn't touch your underlying data." "Safe because it prevents the large language model from caching your data and replicating your business." The tell for any enterprise AI pitch: ask what sits between the model and your data. If the answer is nothing, you are not buying leverage. You are renting a fast way to hand your business to whoever owns the weights. Alex Karp, CEO of Palantir, on CNBC.

Karl Mehta

31,891 views • 2 months ago

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Paul Couvert

18,890 views • 1 year ago

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:

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 views • 2 months ago

Don't waste your time building an Agentic Browser We built an chrome extension that does everything gpt atlas does and more - Can take actions and do things for you right in your own browser - Use 500+ tools like Gmail, Slack, Notion and more - Can be easily accessed in your sidebar Built with Composio Tool Router, Google AI Developers Gemini 2.5 Computer Use and AI SDK Completely free and open source link to the code:

Don't waste your time building an Agentic Browser We built an chrome extension that does everything gpt atlas does and more - Can take actions and do things for you right in your own browser - Use 500+ tools like Gmail, Slack, Notion and more - Can be easily accessed in your sidebar Built with Composio Tool Router, Google AI Developers Gemini 2.5 Computer Use and AI SDK Completely free and open source link to the code:

Karan Vaidya

73,887 views • 10 months ago