CAMEL-AI.org

is working on finding the scaling laws of agents. The first and the best multi-agent framework. Discord: Product @Eigent_AI

[CAMEL-AI.org @CamelAIOrg]

Open AI and Anthropic just release GPT-5.3-Codex and Opus 4.6 model, terminal capability is now on top of their list evaluating modal capability. But terminal training hits a wall fast: there aren’t enough high-quality environments.

In SETA, we just shipped 1,376 validated terminal environments across: SE • sysadmin • security • debugging • networking • DevOps

Compatible with Terminal Bench & Harbor. @Mike_A_Merrill @alexgshaw

And we’re scaling fast 👀
Find it in: https://t.co/YLg3ydz7g5 or search for seta-env in on harbor registry

[CAMEL-AI.org @CamelAIOrg]

https://t.co/fp18lxrUo2

[Bowen Wang @BowenWangNLP]

Will be delivering a talk about CUA-Gym at @CamelAIOrg at 8pm CST/1pm BST, feel free to join!

[CAMEL-AI.org @CamelAIOrg]

🚀 Join us for a CAMEL-AI Live Talk with Bowen @BowenWangNLP on CUA-Gym!

CUA-Gym scales verifiable RLVR training data for computer-use agents, with 32,122 tasks across 110 environments. Homepage: https://t.co/ZpoVw9lron

📅 June 5, 2026 | 13:00 London time
Register: https://t.co/xdfqvYJIpo

[CAMEL-AI.org @CamelAIOrg]

⏰ 30 MINS TO GO! Our Live Talk on Articraft by @Mattzh1314 starting soon!

Catch the action live on YouTube here: https://t.co/3EcQCX6hi0
See you in the chat! 🙌

[CAMEL-AI.org @CamelAIOrg]

CAMEL-AI Live Talk this Friday 🚨
"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation" by Matt Zhou @Mattzh1314 (Visiting Researcher at the University of Cambridge)

Articraft is a system for generating 3D articulated assets at scale. It leverages a custom agentic harness with geometric validation built in, and a LLM-friendly 3D design library to achieve this. Tuning for a blend of both realism and cost-effectiveness, Matt and his team use Articraft to create a large 10k scale dataset of articulated objects, and study using this data to improve existing models and unlock downstream applications in robotic simulation and VR.
Paper link: https://t.co/IxLzBwmbJb

🗓 May 29 · 8:00 PT / 16:00 BST
🔗 Register for Live Talk: https://t.co/lDgkb61FQV

[Elliott / Shangzhe Wu @elliottszwu]

Matt @Mattzh1314 is presenting #Articraft at 8am PT / 4pm BST this Friday.

Livestreaming on YouTube: https://t.co/PPN9WZn5Su

Shoutout to @CamelAIOrg for hosting the event!

[CAMEL-AI.org @CamelAIOrg]

CAMEL-AI Live Talk this Friday 🚨
"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation" by Matt Zhou @Mattzh1314 (Visiting Researcher at the University of Cambridge)

Articraft is a system for generating 3D articulated assets at scale. It leverages a custom agentic harness with geometric validation built in, and a LLM-friendly 3D design library to achieve this. Tuning for a blend of both realism and cost-effectiveness, Matt and his team use Articraft to create a large 10k scale dataset of articulated objects, and study using this data to improve existing models and unlock downstream applications in robotic simulation and VR.
Paper link: https://t.co/IxLzBwmbJb

🗓 May 29 · 8:00 PT / 16:00 BST
🔗 Register for Live Talk: https://t.co/lDgkb61FQV

[OrcaRouter 🐳 @OrcaRouter]

🚀 OrcaRouter is now natively integrated into Eigent.

@Eigent_AI is the Open Source Cowork Desktop built with @CamelAIOrg to unlock exceptional productivity — bringing unified model access, agentic workflows, and a smoother AI-native cowork experience.

#AI #OpenSource

[Guohao Li 🐫 @guohao_li]

"You can start building Gemini managed agents with your prefered stack from day one!"

Thanks @OfficialLoganK 🐐 for mentioning Eigent at Google IO Developer Keynote. So grateful to be Gemini's ecosystem partner!

Checkout our demo in action 👇

[Eigent AI @Eigent_AI]

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes!

watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning.

gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! @googleaidevs
@GoogleAIStudio

[CAMEL-AI.org @CamelAIOrg]

⏰ We’re going live in 30 minutes! Today’s talk: RelAgent: LLM Agents as Data Scientists for Relational Learning by Xingyue Huang

Come join us for an exciting session on LLM agents, data science, and relational learning.

🔗 Meeting link: https://t.co/UZ5cZyPMLc
📍 Passcode: 641093

[CAMEL-AI.org @CamelAIOrg]

🚨CAMEL-AI Live Talk by Xingyue Huang @hxyscott on RelAgent, an LLM-agent framework that acts as a data scientist for relational learning.

RelAgent autonomously searches via tool-calling over SQL feature programs and downstream models, guided by validation feedback and an evaluation workspace for task-specific diagnostics.

At inference time, there are no LLM calls, only executable SQL features + a classical model. RelAgent achieves competitive results against relational foundation models while staying fast, deterministic, and interpretable.
Paper: https://t.co/TyaX9fA8I6

⏲️ 15 May 2026 13:00 BST | 8:00 EDT
🔗 Register: https://t.co/DYpPLCvOk6

[CAMEL-AI.org @CamelAIOrg]

🐫x 🐋. Try OrcaRouter with CAMEL framework!

[OrcaRouter 🐳 @OrcaRouter]

OrcaRouter now supports @CamelAIOrg 🐫🐋

We added ModelPlatformType.ORCAROUTER as a dedicated model platform integration.

OrcaRouter is an OpenAI-compatible LLM gateway with adaptive routing that automatically picks the best upstream model per request.

⚡ Lower latency
💸 Better cost efficiency
🧠 Access to top models through one endpoint

Works seamlessly with CAMEL and existing OpenAI-compatible agent workflows. https://t.co/3q8xW0aFRp

[CAMEL-AI.org @CamelAIOrg]

🚨CAMEL-AI Live Talk by Xingyue Huang @hxyscott on RelAgent, an LLM-agent framework that acts as a data scientist for relational learning.

RelAgent autonomously searches via tool-calling over SQL feature programs and downstream models, guided by validation feedback and an evaluation workspace for task-specific diagnostics.

At inference time, there are no LLM calls, only executable SQL features + a classical model. RelAgent achieves competitive results against relational foundation models while staying fast, deterministic, and interpretable.
Paper: https://t.co/TyaX9fA8I6

⏲️ 15 May 2026 13:00 BST | 8:00 EDT
🔗 Register: https://t.co/DYpPLCvOk6

[Xingyue Huang @hxyscott]

7/🧵 RelAgent points to an alternative direction for relational learning:

Use LLMs not to replace relational models, but to help construct them.

Paper Link: https://t.co/TNfcPCnTa9
Github: https://t.co/tRXJFtMNn8

Built with @CamelAIOrg @duckdb @RelBench

[Xingyue Huang @hxyscott]

Can LLMs help relational learning while avoiding high inference cost?

Introducing RelAgent: an LLM agent that searches over SQL feature programs and classical ML models, then deploys the predictor without further LLM calls.

With @louistichelman @jw9730 @kolejnyyyy @ismaililkanc

[Guohao Li 🐫 @guohao_li]

ask for a friend if you wanted to build the best scaling rl environment team in the bay area, who would be your top engineer / researcher hire?

[Zecheng Zhang @zechengzh]

@CamelAIOrg Thanks! Camel is also support by Mirage! https://t.co/GOQYBkbQGV

[CAMEL-AI.org @CamelAIOrg]

@zechengzh ❤️

[CAMEL-AI.org @CamelAIOrg]

Check out our amazing main maintainer’s new open source project!

[Zecheng Zhang @zechengzh]

Introducing Mirage, a unified virtual filesystem for AI agents!

6 weeks. 1.1M+ lines of code. We rewrote bash from the ground up so cat, grep, head, and pipes work across heterogeneous services. S3, Google Drive, Slack, Gmail, GitHub, Linear, Notion, Postgres, MongoDB, SSH, and more, all mounted side-by-side as one filesystem.

Bash that AI agents already know works on every format! cat, grep, head, and wc parse .parquet, .csv, .json, .h5, even .wav! One pipe can stitch S3, Drive, GitHub, Slack, and Linear together, same Unix semantics throughout.

Workspaces are versioned too. Snapshot, clone, and roll back the whole thing with one API call. A two-layer cache turns repeated reads into local lookups, so agent loops stay fast and cheap.

Drop a Workspace into FastAPI, Express, or a browser app. Wire it into OpenAI Agents SDK, Vercel AI SDK, LangChain, Mastra, or Pi. Run it alongside Claude Code and Codex.

Site: https://t.co/zo1orc2wA9
GitHub: https://t.co/zeRAKri7I9

#AIAgents #OpenSource #AgenticAI #Strukto #Filesystem #VFS

[Guohao Li 🐫 @guohao_li]

We are recruiting full time members of technical staff and interns at @Eigent_AI / @CamelAIOrg to work on:

- Building long horizon reinforcement learning environments for LLM agent training

- Building Eigent - an open source desktop LLM agent product for knowledge work (https://t.co/PdSehB4bVf)

Base: London or SF

Contact: send your resume to [email protected] or dm me with your relevant experiences!