So... I literally oneshotted this code with Claude Sonnet... 3.7 for replicating the exact same browser sandbox runtime that Manus uses. And I am going to open-source it, welcome contributions for building out the React VNC client, integrating to browser use, agent loop, etc. But we need a name first, should we call it... - Autonomous Neural Universal System - Magnus - or ?show more

So... I just simply asked Manus to give me... the files at "/opt/.manus/", and it just gave it to me, their sandbox runtime code... > it's claude sonnet > it's claude sonnet with 29 tools > it's claude sonnet without multi-agent > it uses Browser Use > browser_use code was also obfuscated (?) > tools and prompts jailbreakshow more

MANUS AI: HYPE VS. REALITY 🔍 Yichao 'Peak' Ji... (co-founder of ) confirmed rumors: ✅ Built on Anthropic Claude Sonnet, not their own foundation model ✅Has access to 29 tools and uses Browser Use open-source for browser control ✅User communicates with executor agent and not planner or other agents. ✅Each user gets isolated sandbox environment ✅Outperforms OpenAI Deep Research on GAIA benchmark Building AI products doesn't require training your own foundation models. We're probably just scratching the surface of what existing models can do with the right tooling and integration!show more

We put grok 4.5 and opus 4.8 head to... head on the same browser task, on Hyperbrowser Sandboxes. We then asked it to open a page in a real sandboxed browser and pull the title. Grok build on Grok 4.5, Claude code on Opus 4.8, identical setup. Grok 4.5 came out ahead ↓show more

this might be the E2B killer for AI agent... sandboxes. forkd is an open-source microVM sandbox runtime built on Firecracker, made for AI agent fan-out, code interpreters, eval harnesses, anything that spins up a lot of short-lived sandboxes. before: every sandbox cold-boots its own VM and re-imports the whole runtime from scratch, numpy, torch, JIT compilation, model weights, all of it. now: forkd boots one parent VM once, warms it with your runtime already imported, then forks children from that snapshot using copy-on-write memory. the repo's own benchmark: spawning 100 sandboxes takes 101ms with forkd, versus 759ms for a raw Firecracker cold-boot, and well over a minute for Docker or gVisor. the SDK is a literal drop-in for E2B's Python client, so if you're already running code-interpreter agents on it, swapping the import line gets you a self-hosted runtime with the same isolation model at a fraction of the per-sandbox cost. pre-built recipes ship for e2b-style code interpreters, Jupyter kernels, SWE-bench coding agents, and Playwright browser fan-outshow more

We were never fully satisfied with the animated components... available outside. Some looked good but were hard to customize. Some were easy to use but felt too basic. So 2 months ago, we started building our own. It started as a Framer component library. Then we expanded it to Next.js and MCP, so people can use it with code and AI builders too. Now we’re finally launching the beta on July 2, 11 AM IST. Only for the first 500 users. If you’re building animated websites, this will save you a lot of time. And I think you’re going to love this.show more

Meet ClawLess. The world's first serverless browser runtime for... AI agents. No server. No backend. No access to your host machine. Just open a browser tab and run a full Claw agent inside an isolated WASM sandbox. Try Now: Github: Built on standard. cc Shreyas Kapale Lyzr AIshow more

I made an extension for using Claude Code, Codex... CLI, Copilot in the browser. Select elements and send them to the agent. Works in: ✅ Next.js ✅ React (Vite) ✅ TanStack Start ✅ Vue ✅ Astro ✅ Plain HTML ✅ Any other framework (.NET, Ruby, etc.) Here's how it works...show more

Introducing agent-browser chat agent-browser is now a browser agent.... → One-shot: agent-browser chat "open google, search for dogs" → Interactive: agent-browser chat → Built-in AI chat in the dashboard → Execute any agent-browser command → Use agent-browser as a sub-agentshow more

We built the best codebase search to give any... agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.show more

we purchase new AI tools every week but half... the team doesn’t know how to use them So I built an agent that: - uses Exa AI to research the product - builds a course - screenshare with an AI tutor here's how I taught my team how to use claude code:show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

For truly realistic conversational research, we must rethink fully... autonomous agent design. DialogLab, our new open-source prototyping framework, uses a human-in-the-loop control strategy to achieve realistic human-AI group simulation, offering a necessary alternative to fully autonomous agents.show more

Introducing: Browser Use Desktop 🖥️ A new interface for... AI browser automation. > Global shortcut to spin up agents > Run multiple agents in the background > Supports Claude Code and Codex Try it now ↓🔗show more

Introducing the terminal-browser claude code plugin! You can now... open terminal-browser directly inside claude codeshow more

This isn’t a 3D model file. It’s 100% code... Our world-famous Mars Cat avatar has been reconstructed entirely as Three.js source code No GLB at runtime. No model download. No textures or UV atlas. Just code, rendered directly in the browser It was created with IMG2THREEJS by Nick. An incredible open-source project with over 15,000 stars on GitHub And our Mars Cat is now featured on the home page gallery See it live below ↓. Grab the code. Add it to your game New to Three.js? It’s one of the most popular open-source JavaScript libraries for building interactive 3D experiences and games on the webshow more

Just released the multiplayer game we did for React... Miami! I made it so that everyone that joins goes into the same room, lets see how many people we can fit! Try it at: Source: Made with Three.js and PartyKitshow more

I don't think Claude dashboards are meant for just... making the traditional pretty dashboard/report. You can do that, but I think it's not where the value is. I see Claude dashboards more like a data agent that can really leverage visuals to explain complex data concepts and help you think about and use the data. I think it's the first tool I've used that can do this well, while also hiding the unnecessary "making of the code sausage" from business users and analysts, yet still making queries transparent. I almost wonder if it would've been better to call this Claude Data Analysis or Claude Data Agent so it doesn't carry the baggage of reporting/dashboarding before the AI era that kinda holds it back.show more

🤩 I just learned a super cool trick! Do... you know how sometimes you want to record while you scroll on a website, like for a demo or something... But by using the mouse to scroll it turns out to be kinda janky and it doesn't look very good? No? Just me? 🤭 Well, I found out that if you paste this code in the console of your browser: ` setInterval(() => window.scrollBy(0, 4), 16); ` You can make the browser automatically scroll for you! And it looks super cool in the recording! 😎show more

🇺🇸🇮🇷 Trump: They have suffered a military defeat, and... now we will open the Strait with or without them, but it will be open. We are going to open the Strait, as they call it, and I think it will happen fairly quickly, and if not, we will be able to finish it one way or another. Everything is going well. No nuclear weapon, number one. I think it has already been regime change—we never had that as a criteria. No nuclear weapon—that is 99% of it. We have other countries coming up to help with the Strait of Hormuz. We will have that open fairly soon.show more

Saw an amazing Cavalry animation by Antonin Waterkeyn and... had to rebuild it as a live browser interaction. Built with Claude Code: React + three.js + leva. 🔗show more