Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Calibre library automation via FastMCP — metadata, shelves, RAG-friendly export. Companion to Calibre, not a replacement. For Cursor / Claude Desktop.

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.

Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.