Arachne

Assembles optimized codebase context for AI coding by selecting only relevant files through hybrid search and dependency graph analysis.

Indexes a project codebase into a local SQLite database and assembles precisely targeted context using a 4-layer system: project tree overview, current files, search results with dependency chain traversal, and frequently accessed files. Supports BM25 keyword search with optional semantic vector search via Ollama embeddings, and follows import chains across JavaScript, TypeScript, Python, Rust, Go, and Java. Achieves significant token reduction while maintaining accuracy through intelligent file selection.