#tree-sitter

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Local semantic code graph + MCP server for AI coding agents (Rust, Tree-sitter, SQLite)

Pure CLI, zero-MCP, stateless context layer for AI coding agents: tree-sitter AST symbol slicing and exec output compression, byte-stable for prompt caching.

Production-ready AI Coding Agent built with LangGraph, Groq, Code RAG, Tool Calling, FAISS, Tree-sitter, and Docker. Supports code understanding, retrieval, editing, terminal execution, and debugging.

The editor for the rest of us — a fast, native code editor written in Rust, with first-class PHP/Laravel support, an integrated terminal, and an AI agent panel.

MCP server that gives AI coding agents persistent memory of your codebase: notes pinned to files, spans, and symbols that survive refactors. Works with Claude Code, Cursor, and any MCP host.

Deterministic proof that an AI coding agent built what the plan said it would.

Fastest agentic search substrate. S3-native ls/glob/read/grep with tree-sitter spans, parallel fan-out, MCP server. Rust.