High-performance AST repository indexer & SQLite graph database for AI coding agents
✓ Verified Proof of Concept ReadyFastAST is an ultra-fast, AST-based repository indexer designed for AI coding agents and developers. Instead of reading whole repositories blindly or relying on fuzzy regex grep, FastAST parses code into syntax trees across 9 languages using native Tree-Sitter and indexes all files, symbols, imports, and function calls into a persistent SQLite database.
AI coding agents connect via the standard Model Context Protocol (MCP) to query symbol definitions, find references, and explore call graphs instantly without exhausting token context budgets.
Parses source files into Tree-Sitter AST nodes across 9 languages (Python, Java, JavaScript, TypeScript, Rust, HTML, CSS, JSON, TOML).
Extracts classes, methods, functions, module imports, and invocation calls into structured FileIndexResult structs.
Walks the repository honoring ignore rules (.git, node_modules, target, .venv).
Populates indexed tables (files, symbols, imports, calls) and provides high-speed query methods (find_symbol, get_calls_from_symbol).
Connects coding agents and developers to the index. Exposes index_repository, query_symbols, and get_call_graph over stdio JSON-RPC for Claude Code and Cursor, plus terminal CLI commands (index, symbols, calls).
Cargo.toml and implement index_code in src/<lang>/mod.rs.RepositoryIndexer.init_db() in python/fastast/indexer.py.@mcp.tool() endpoints in python/fastast/server.py.DEFAULT_IGNORES in python/fastast/indexer.py.# 1. Index a repository:
fastast index . --db fastast.db
# 2. Query symbols:
fastast symbols fastast.db --query "index"
# 3. Trace call graph:
fastast calls fastast.db --symbol "main"
# 4. Start the MCP server:
fastast-mcp --db fastast.db