Multi-server MCP aggregator with 266 skills, an orchestration runtime, fleet/claims coordination, and hook-driven session governance for autonomous Claude/Cursor/Gemini agent runs.
Universal AI Agent OS — governed skills, rules, and commands for AI coding assistants (Claude Code, Augment, Cursor, Copilot, Windsurf). Read-only MCP bridge serves prompts and resources from a release-pinned content bundle.
A local-first skill runtime for AI coding agents that defines skills as verifiable, composable units with sandboxed execution, and exposes them as MCP tools over HTTP.
A full-stack Agent project built from the JSON-RPC protocol layer to the LLM orchestration layer, featuring a custom ReAct loop engine, dual Provider abstraction, and permission control for Agent scenarios.
Enables offline AI agent automation with embedded local LLM (Qwen 2.5), sandboxed file operations through AgentFS, and dynamic skill loading. Exposes capabilities via MCP with tri-state safety guards for private, air-gapped environments without network connectivity or API costs.