
CAMEL-AI.org
1.4K posts

CAMEL-AI.org
@CamelAIOrg
https://t.co/FmX1B3nzjA is working on finding the scaling laws of agents. The first and the best multi-agent framework. Discord: https://t.co/DRweXf0nOl. Product @Eigent_AI




Built a tweet optimizer as a side project for week 1 of @interviewkick's Agentic AI program. I used @CamelAIOrg's OASIS project and was inspired by @karpathy's autoresearch. Here's how it works: Paste a tweet, describe your audience. OASIS spins up 100 synthetic personas (lurkers, curators, debaters, reply guys) each deciding to like, repost, reply, or do nothing. Engagement gets scored, a refiner edits the tweet, runs it again. 20 iterations. Then I ran a tweet about the tool through the tool. Round 3 peaked at a score of 4. One repost, one like. 17 more iterations couldn't beat it. The agents were not impressed. 🤣

MiroFish recently ranked #1 on GitHub Trending. The multi-agent social simulation behind it? Built on OASIS. 🏝️ This Friday, we're bringing OASIS first author Ziyi Yang to CAMEL Live Talk 📢 to break down how you simulate 1 million LLM agents and what it reveals about how information spreads across social networks. Join us to explore OASIS and social interaction simulation! 🔗Register: forms.gle/pSTPLe4LK2r26y…





Where is the abnormality? Diagnosis? This xray is not normal. (Source: J of Urgent Care)



🚨 CAMEL AI Live Talk this Friday: Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations with Wei Liu Join the CAMEL-AI 🐫 Community to explore Dr. Kernel, a reinforcement learning framework for generating high-performance Triton kernels, enabling scalable GPU-based training and profiling-driven rewards to produce optimized code beyond standard LLM baselines. ⏲️ Time: 27th Feb | GMT 13:00 | EST 8:00 | CST 21:00| 📍 Location: Google Meet 🔗 Register: forms.gle/TAvK5kDcLHU2hd…

CLIs are super exciting precisely because they are a "legacy" technology, which means AI agents can natively and easily use them, combine them, interact with them via the entire terminal toolkit. E.g ask your Claude/Codex agent to install this new Polymarket CLI and ask for any arbitrary dashboards or interfaces or logic. The agents will build it for you. Install the Github CLI too and you can ask them to navigate the repo, see issues, PRs, discussions, even the code itself. Example: Claude built this terminal dashboard in ~3 minutes, of the highest volume polymarkets and the 24hr change. Or you can make it a web app or whatever you want. Even more powerful when you use it as a module of bigger pipelines. If you have any kind of product or service think: can agents access and use them? - are your legacy docs (for humans) at least exportable in markdown? - have you written Skills for your product? - can your product/service be usable via CLI? Or MCP? - ... It's 2026. Build. For. Agents.

New in Cowork: scheduled tasks. Claude can now complete recurring tasks at specific times automatically: a morning brief, weekly spreadsheet updates, Friday team presentations.



Introducing Cowork and plugin updates that help enterprises customize Claude for better collaboration with every team.

Eigent supports Gemini 3.1 Pro on day 0. @GoogleDeepMind Watch our open-source coworker spin up a Mario-style Snow Bros game in minutes using the Developer Agent powered by Gemini 3.1 Pro. You can interact with it directly on Eigent! Available on the Eigent GitHub main branch: github.com/eigent-ai/eige…


Eigent × Ming-flash-omni 2.0 @AntLingAGI @TheInclusionAI Robot With a Sword… Now in Comic Form We dropped “Unnerving sword-wielding robot dances for Chinese New Year stunt” to our open source cowork, powered by Ming-flash-omni 2.0. With video-to-text and image generation skills, the Video Agent first converted the performance into structured descriptions, then image agent generate a set of comic-style images Cold steel. Red lantern vibes. Dramatic poses. Watch the video to see it in action!