Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj
MCP server that maps source files into a normalized code skeleton (JSON + HTML) using tree-sitter.
TypeScript types for CodeMap custom tools (.tool.ts)
Pi extension for readseek-backed hash-anchored read/edit/grep, structural code maps, structural search, and file exploration