17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.
Proof-backed, drift-resistant AI memory for your codebase. 11 languages, 28 MCP tools, evidence-linked claims.
AST-powered codebase indexer skill for coding agents. Spelunk parses repositories with Tree-sitter into a local SQLite index so agents trace dependency trees and locate symbols in under 100ms instead of scanning raw files. Reduces token consumption by up to 90% with instant symbol resolution.
A Claude skill that indexes codebases with minimal context‑window overhead using tiered memory.
Deterministic local code context for coding agents.
Local-first semantic memory layer for codebases. Indexes Git repositories and exposes search capabilities via MCP to coding agents.
A fast, deterministic codebase indexer that maps natural-language queries to project files. Features include real-time watch mode, semantic search with synonym caching, quality evaluation metrics (Hit@k, MRR), and health checks. Built in Go for LLM agents.
Add a description, image, and links to the codebase-indexer topic page so that developers can more easily learn about it.
To associate your repository with the codebase-indexer topic, visit your repo's landing page and select "manage topics."