CAMEL-AI.org

x.com/i/article/2009…

🚨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: arxiv.org/abs/2605.07840 ⏲️ 15 May 2026 13:00 BST | 8:00 EDT 🔗 Register: forms.gle/Myjx7A4URqp9Q7…

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. github.com/camel-ai/camel

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: strukto.ai/mirage GitHub: github.com/strukto-ai/mir… #AIAgents #OpenSource #AgenticAI #Strukto #Filesystem #VFS

That's it for now! Let us know if you'd like your environment or evaluation to be featured next week. The most popular environment last week was SETA from @Eigent_AI with 855k tool calls via the @OpenReward API.

That's it for now! Let us know if you'd like your environment or evaluation to be featured next week. The most popular environment last week was SETA from @Eigent_AI with 855k tool calls via the @OpenReward API.

Join us for an exclusive deep dive into 𝐃𝐨𝐥𝐚 𝐒𝐞𝐞𝐝 2.0, the multimodal core of the Seed ecosystem. In this session, Bojie Sun and Ron Wang from BytePlus will unpack the foundation behind Seed’s frontier video model and how teams can build with a unified stack across text, vision, video, and agent workflows. You will also see real-world demos from ecosystem partners @Tiny_Fish, @Eigent_AI, and @kilocode, covering browser use, computer use, and agentic task execution in action. - @Tiny_Fish: VLM-assisted deep browsing for web research and information structuring - @Eigent_AI: Computer use for enterprise systems, including SAP and Salesforce workflow automation - @kilocode: Agentic task execution for reasoning, instruction following, and real-world task completion LIVE: Apr 2, 2026 @ 20:00 EDT / 17:00 PDT 🚨