https://xitter.cf/t.co/FmX1B3nzjA is working on finding the scaling laws of agents. The first and the best multi-agent framework. Discord: https://xitter.cf/t.co/DRweXf0nOl. Product @Eigent_AI
Joined June 2023
- Tweets1.5K
- Following96
- Followers8.7K
- Likes1.7K
Pinned Tweet
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: github.com/camel-ai/seta-env or search for seta-env in on harbor registry
CAMEL-AI.org retweeted
We're releasing AgentVFS, a virtual filesystem interface for AI agents agentvfs.org/
AgentVFS unifies every service into one interface and replaces the need of calling MCP. Stored data becomes one virtual filesystem across services, described by VFS.md, and actions become virtual CLIs, so the agent no longer calls MCP tools at all. AI agents work on live data across every service through the terminal-like interface they know best. They use the Unix tools they learned in training (ls, grep, jq, pipes, loops) and the terminal workflows they practiced in post-training on agentic coding.
We're also releasing VFS-Bench 1.0 agentvfs.org/benchmark/vfs-b…, the first systematic study and benchmark to compare a virtual filesystem with MCP on the same tasks. Compared with MCP, AgentVFS uses up to 88% fewer tokens and has about a 5% higher success rate on average.
CAMEL-AI.org retweeted
What if every SaaS service could be virtualized as files? Excited to release AgentVFS and VFS-Bench 1.0 with @zechengzh: a virtual filesystem interface for AI agents, and the first systematic benchmark comparing it against MCP on the exact same tasks
One task, two interfaces: VFS v.s. MCP. 200 tasks from MCP-Atlas and Toolathlon. Every task runs once through MCP tools and once through AgentVFS, where services show up as files described by VFS.md and actions become CLIs
What we found:
- Claude Opus 5.5: 86% vs 83% pass@1, with 166k vs 617k tokens per task (73% fewer)
- GPT-6.1 Sol: same 75% success, 72% fewer tokens
- GPT-5.6 Luna: 61% → 73% success, 60% fewer tokens
- Up to 88% fewer tokens, and about 5% higher success on average
The part I find most interesting: stronger models gain the most. Opus and Sol save over 70% of their tokens, while smaller models save much less. Frontier models were post-trained heavily on terminal-style coding, and they seem to bring all of it to ls, grep, jq and pipes once you give them that interface
We spend all day building RL environments for agents. One lesson keeps coming back: the interface is part of the environment. The same task can get much easier or much harder depending on how you expose the world to the model
An AgentVFS layer may be how we scale environments for agents. One filesystem in front of every service, and the terminal skills models already have carry over to all of them
We're releasing AgentVFS, a virtual filesystem interface for AI agents agentvfs.org/
AgentVFS unifies every service into one interface and replaces the need of calling MCP. Stored data becomes one virtual filesystem across services, described by VFS.md, and actions become virtual CLIs, so the agent no longer calls MCP tools at all. AI agents work on live data across every service through the terminal-like interface they know best. They use the Unix tools they learned in training (ls, grep, jq, pipes, loops) and the terminal workflows they practiced in post-training on agentic coding.
We're also releasing VFS-Bench 1.0 agentvfs.org/benchmark/vfs-b…, the first systematic study and benchmark to compare a virtual filesystem with MCP on the same tasks. Compared with MCP, AgentVFS uses up to 88% fewer tokens and has about a 5% higher success rate on average.
CAMEL-AI.org retweeted
Eigent v1.0.6 is live! Models, Automations, and Session recovery just got a major upgrade 🚀
What’s new:
🧠 Manage saved models in one place
⏰ Inspect Automation schedules and run history
👋 Choose your Work Profile
🔄 Recover Sessions and handle approvals more reliably
📂 Preserve drafts, terminal history, and finished files
📦 Validate Bundles before sharing and recover failed imports
🔁 Follow clearer upgrade guidance
❤️ Enjoy more control over everyday work
Update to v1.0.6, explore the new features and share your feedback with us 🙌
Read the full release notes: eigent.ai/blog/eigent-v1-0-6…
CAMEL-AI.org retweeted
@Eigent_AI is proud to be part of the SGLang Summit! Come talk to us about RL × Environments × Agents!
Proud to welcome our newest sponsors to SGLang Summit.
In just one week since our public announcement, our sponsor lineup has grown from 11 to 36. Thank you to every sponsor helping bring this community together.
Join 2,000+ engineers, researchers, and builders from across the AI ecosystem for technical sessions, hands-on workshops, and the GPU Expo.
Hear from Lip-Bu Tan, Lilian Weng, Soumith Chintala, Aravind Srinivas, and more. Meet the teams building across AI hardware, infrastructure, models, and applications.
🗓️ November 12–13, 2026
🌉 Fort Mason, San Francisco
🎟️ Get your tickets: sglang.io/summit
CAMEL-AI.org retweeted
Proud to welcome our newest sponsors to SGLang Summit.
In just one week since our public announcement, our sponsor lineup has grown from 11 to 36. Thank you to every sponsor helping bring this community together.
Join 2,000+ engineers, researchers, and builders from across the AI ecosystem for technical sessions, hands-on workshops, and the GPU Expo.
Hear from Lip-Bu Tan, Lilian Weng, Soumith Chintala, Aravind Srinivas, and more. Meet the teams building across AI hardware, infrastructure, models, and applications.
🗓️ November 12–13, 2026
🌉 Fort Mason, San Francisco
🎟️ Get your tickets: sglang.io/summit
We're starting in 10 minutes! Join us for Zihan @CrD104 's Live Talk on CAD World.
🔗 Zoom: us06web.zoom.us/j/8190844404…
📢 Join our CAMEL-AI Live Talk next Friday with Zihan Dong @CrD104 , AI Solutions Engineer at Lenovo, presenting CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design
He'll introduce CADWorld, a benchmark that evaluates how effectively AI agents can perform realistic mechanical CAD workflows by operating professional software directly through its GUI. It includes 200 tasks across 11 workflow categories, covering the end-to-end design process from modeling and assembly to manufacturing and simulation.
📅 October 16, 2026
🕐 14:00 BST | 9:00 EDT | 21:00 CST
🔗 Register: docs.google.com/forms/d/1Ow1…
🐫 If you're interested in computer-use agents, CAD, or AI for engineering, don't miss this talk!
CAMEL-AI.org retweeted
Gemini 4 directed a multi-shot 3D Blender scene on Eigent! 🎬
From a calm setup to a delicate wind-blown flight and final landing. 4 connected shots, dynamic DOF, and consistent physics constraints in just one prompt!
Build effortless 3D creations today on Eigent via byok & cloud API!
Today we are rolling out Gemini 4 Argon globally in the Gemini API, to Pro + Ultra in Gemini App, and Ultra subs in Antigravity!
Argon is a huge step forward for Gemini, and a labor of love. This model has been battle tested by over 100,000 people at Google over the last month, with so much new innovation, ambition, and hard work baked into this release. The team has been heads down over the last 6 months working to make this possible across the stack (research, infra, safety, eng, etc).
We rolled the model out to cyber defenders as part of our fairwind program and early access customers over the last 2 weeks, it has been amazing to see and talk to folks who are now using this model daily. Seeing the models writing capability, raw knowledge and persistence for coding, paired with new features like 1M token output when the model needs to work more has gotten me even more excited about our path ahead.
This is just the start of the Gemini 4 era. As you saw with 3.5, 3.6, 3.7, and 3.8 Flash, our iteration speed with Gemini is fast : ) Now with Gemini 4 Argon to work from, I am cannot wait to see the progress continue, and most importantly see what this new model enables for the world.
This is such a special moment in the arc of technology, as millions of people everyday tackle problems they could never have thought possible before. Gemini 4 Argon was built to help you tackle the hardest problems. I have personally felt this spark with Argon and hope you do too. Onwards!!
CAMEL-AI.org retweeted
Gemini 4 Argon is now on Eigent!!
It turns terminal bench author's insights into agent skills in one prompt!
👉 understands RL videos -> extracts key insights with precise timestamps -> produces validated agent skills plus a structured HTML report
Add your Gemini API key on Eigent and try it today!
Today we are rolling out Gemini 4 Argon globally in the Gemini API, to Pro + Ultra in Gemini App, and Ultra subs in Antigravity!
Argon is a huge step forward for Gemini, and a labor of love. This model has been battle tested by over 100,000 people at Google over the last month, with so much new innovation, ambition, and hard work baked into this release. The team has been heads down over the last 6 months working to make this possible across the stack (research, infra, safety, eng, etc).
We rolled the model out to cyber defenders as part of our fairwind program and early access customers over the last 2 weeks, it has been amazing to see and talk to folks who are now using this model daily. Seeing the models writing capability, raw knowledge and persistence for coding, paired with new features like 1M token output when the model needs to work more has gotten me even more excited about our path ahead.
This is just the start of the Gemini 4 era. As you saw with 3.5, 3.6, 3.7, and 3.8 Flash, our iteration speed with Gemini is fast : ) Now with Gemini 4 Argon to work from, I am cannot wait to see the progress continue, and most importantly see what this new model enables for the world.
This is such a special moment in the arc of technology, as millions of people everyday tackle problems they could never have thought possible before. Gemini 4 Argon was built to help you tackle the hardest problems. I have personally felt this spark with Argon and hope you do too. Onwards!!
📢 Join our CAMEL-AI Live Talk next Friday with Zihan Dong @CrD104 , AI Solutions Engineer at Lenovo, presenting CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design
He'll introduce CADWorld, a benchmark that evaluates how effectively AI agents can perform realistic mechanical CAD workflows by operating professional software directly through its GUI. It includes 200 tasks across 11 workflow categories, covering the end-to-end design process from modeling and assembly to manufacturing and simulation.
📅 October 16, 2026
🕐 14:00 BST | 9:00 EDT | 21:00 CST
🔗 Register: docs.google.com/forms/d/1Ow1…
🐫 If you're interested in computer-use agents, CAD, or AI for engineering, don't miss this talk!
Thank everyone who contributed to SETA! Check it out if you are working on terminal agent RL: github.com/camel-ai/seta
SETA got accepted to NeurIPS 2026! 🎉
We released the full training scripts for DeepSeek-V4-Flash, GLM-5.2 (LoRA), Inkling-Small, and Qwen3.8-27B, with both GRPO and PPO, alongside 4,500+ open-source, verifiable terminal RL environments
Huge thanks to the @radixark Miles team for helping us scale the experiments!
github.com/camel-ai/seta/tre…
CAMEL-AI.org retweeted
SETA got accepted to NeurIPS 2026! 🎉
We released the full training scripts for DeepSeek-V4-Flash, GLM-5.2 (LoRA), Inkling-Small, and Qwen3.8-27B, with both GRPO and PPO, alongside 4,500+ open-source, verifiable terminal RL environments
Huge thanks to the @radixark Miles team for helping us scale the experiments!
github.com/camel-ai/seta/tre…
🎉 SETA: Scaling Environments for Terminal Agents has been accepted to the #NeurIPS2026 Evaluations & Datasets Track!
We release SETA-Env, the largest open-source verifiable terminal RL dataset (4,500+ envs), with full synthesis & training pipelines 🧵
arxiv.org/abs/2607.10891
Thanks for highlighting our work. Great work @AtriaASI!
We’re excited to highlight SETA, an open-source RL environment for training and evaluating AI agents from the @CamelAIOrg .
A valuable resource for researchers and developers exploring agentic reinforcement learning and complex task environments.
Check it out and support the CAMEL-AI community! 🚀
🔗 github.com/camel-ai/seta
CAMEL-AI.org retweeted
@OpenAI GPT 6 Astra is now on Eigent! ⚡️⚡️⚡️
Our design engineer @douglas_ym used Eigent with GPT 6 Astra to rebuild his old master’s project, TaSH, from just a few photos of the original prototype.
Eigent recreated the full product in Blender, filled in details missing from the original prototype, and automatically rendered a 30-second @Apple style product showcase video.
Download Eigent today. Give Eigent a few images from one of your forgotten projects and see what GPT 6 Astra can rebuild.
Fully open source. Self-hostable on your desktop. Even for confidential projects, your data can stay completely under your control.
We are starting in 5 mins! Come join us 🐫
Zoom Meeting ID: 872 7159 9220
Passcode: 886353
This Friday on 🐫 CAMEL-AI Live Talk, Ziyi Wang @Ziyi0_0 is sharing Trajectory2Task: a trajectory-first way to train stronger tool-calling agents with synthesized, verifiable data.
Instead of writing tasks first and hoping agents can solve them, Trajectory2Task starts with executable tool-use trajectories, then turns their outcomes into realistic user intents. The result: training data that is diverse, grounded, and actually checkable.
If you care about LLM agents, tool use, or synthetic data for post-training, don’t miss this one!
🗓️ Sep 4 · 4 PM UK Time / 8 AM PT · Zoom
📝 Register: forms.gle/aqTzxMy9KqauHQj28
This Friday on 🐫 CAMEL-AI Live Talk, Ziyi Wang @Ziyi0_0 is sharing Trajectory2Task: a trajectory-first way to train stronger tool-calling agents with synthesized, verifiable data.
Instead of writing tasks first and hoping agents can solve them, Trajectory2Task starts with executable tool-use trajectories, then turns their outcomes into realistic user intents. The result: training data that is diverse, grounded, and actually checkable.
If you care about LLM agents, tool use, or synthetic data for post-training, don’t miss this one!
🗓️ Sep 4 · 4 PM UK Time / 8 AM PT · Zoom
📝 Register: forms.gle/aqTzxMy9KqauHQj28
CAMEL-AI.org retweeted
Gemini 3.8 now on Eigent! ⚡️⚡️⚡️
We handed it a real finance analyst's job: value Equinix vs Digital Realty, Damodaran-style, straight from SEC filings.
A team of agents researched, checked FX, and built the DCF, then handed back an Excel file you can actually poke at.
Click a number → see the filing it came from. Change an assumption → watch the valuation shift live.
Gemini 3.8 is now supported on Eigent via BYOK and cloud API. Try it today！
Huge congrats to the incredible @radixark team on the launch of Miles v0.1! We've really enjoyed using it in our research projects such as SETA: github.com/camel-ai/seta/tre…
Today we're launching Miles v0.1, an open-source RL framework for LLMs and multimodal models.
RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale.
Over the past 9 months, 72 contributors have landed 1,326 commits, 85 GPU E2E CI tests, battle-testing Miles on frontier open models like Kimi K3, DeepSeek V4, Qwen 3.8, GLM 5.2, Inkling, MiniMax H3, etc.
Miles powers frontier-model development and production RL workloads at @humansand, @periodiclabs, @modal, @DecagonAI, @Eigent_AI, @nebiusai, @IBM and more, on both @NVIDIAAI and @AIatAMD hardware.
Here is what we built, and why teams picked Miles🧵
CAMEL-AI.org retweeted
Gemini 3.7 Flash now live on Eigent on both byok and cloud api ⚡️
Lightning speed meets unbelievable precision:
> Video-to-3D understanding
> Ultra-detailed, articulated CAD/mesh models (.glb)
> Full PBR materials & emissive lighting
From video reference to production-ready 3D in 3 mins! We also did a comparison with 3.6 Flash it's 2x faster and delivers far richer, more accurate details! 🚀
Download Eigent with free credits to build your own 3D models today!
We’re starting in 30 minutes! If you're working on model evaluation, LLM testing, or agent diagnostics, come join CAMEL-AI Community Live Talk by @NishantBalepur! 🐫
Meeting Info👇 us05web.zoom.us/j/8573785877…
Meeting ID: 85737858776 Passcode: Hz3cR1
This Friday on 🐫 CAMEL-AI Live Talk, Nishant is unveiling BenchMarker, and it might change how much you trust your favorite benchmarks. He is an NLP PhD candidate at the University of Maryland who cares about making LLM evaluation actually mean something.
The idea is simple but sharp: grade benchmarks the way teachers grade exam questions. BenchMarker uses LLM judges to catch three sneaky flaws in multiple choice tests, internet contamination, shortcuts models quietly exploit, and writing errors scored against a 19 rule rubric. Validated against human annotations and run across 12 popular benchmarks, the flaws showed up everywhere.
If your work touches evaluation, LLM testing, or agent diagnosis, this one is for you.
🗓 Jul 31 · 1 PM UK (BST) / 8 AM US East (EDT) · Zoom
📝 Register: docs.google.com/forms/d/e/1F…
