Ratel: context engineering and tool selection for AI agents
An in-process context engineering platform that selects which tools enter an AI agent's context window each turn, using BM25 retrieval without a vector database or embeddings.
online BOTH AI Agents & Automation
From ManuAGI - AutoGPT Tutorials — Top Open-Source GitHub Projects : bitchat, Dokku, Mole, Box3D, Kaneo & GeoLibre #279 at 09:57
Problem: Showing every available tool to an agent can overload its context window and obscure the tools relevant to the current turn.
For: Developers operating AI agents with many tools or MCP servers.
Products from this video
Awesome LLM Apps bitchat book-to-skill Box3D Decimen Optical Transfer Dokku Experiential GeoLibre Hubble.md Impeccable Kaneo last30days Native SDK OpenSlides quill Ratel Unsloth Zoo
Other takes on AI agent platforms and compute access
- Autonomous AI agents that perform administrative labor for underserved small businesses, starting with dental practices
- A personal, open-source AI agent that can be operated through messaging channels such as WhatsApp and Discord
- Enterprise AI concierge for customer, sales, and operational workflows
- AI appointment-scheduling assistant for healthcare providers
- Production-ready inference hosting for open AI models
- A cloud-hosted AI co-founder club that gives each member a personal, containerized AI agent
All AI agent platforms and compute access ideas →