A self-hosted multi-tenant knowledge agent platform: unified RAG, knowledge graphs, multi-agent workflows, MCP/Skills, sandboxing, and permission management. Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
Yuxi is a self-hosted, multi-tenant knowledge-agent platform that combines document retrieval, knowledge graphs, multi-agent workflows, tools, sandboxes, and access controls in one workspace. Teams use it to build source-backed question answering and multi-step agents while managing their data, models, and permissions. The catalogue entries provide agents, skills, and instructions for Yuxi workflows.
Latest release v0.7.2 — v0.7.2 正式版 · 2 Sept 2026
2 files for Codex, OpenCode and Claude Code: Yuxi AGENTS.md, Yuxi CLAUDE.md — 2,299 tokens loaded in every session.
AGENTS.md A 2,296 tok CLAUDE.md A 3 tok These files are xerrors/Yuxi's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.