VerbalCodeAI is a free, open-source AI tool that simplifies codebase navigation in your terminal, using Python 3.11.6 and Ollama. It indexes projects locally and quickly answers questions like “Where’s this function?”, saving developers time on debugging and onboarding.

CodeCompass: AI-powered Vibe Coding with MCP. Connects Git repositories to AI assistants like Claude, using Ollama for privacy or OpenAI for cloud. Integrates with VSCode, Cursor, and more.

Token-efficient codebase maps for AI IDEs. Parses Python, TypeScript & more with tree-sitter, builds a ranked dependency graph, and exposes it via MCP to Cursor, VS Code, and Claude Desktop.

MCP server for code intelligence - maps source code into a knowledge graph so AI tools understand architecture, not just files. Built in Rust.

A lightweight file-mapping standard that lets any AI tool navigate large codebases without reading every file. One index, two rules, any AI. No more wasted tokens, no more wasted time.

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.

CodeGraphX (CGX) — a local, token-efficient codebase graph engine & MCP server for AI coding agents. Tree-sitter parsing, a bi-temporal SQLite semantic graph, O(1) symbol lookup, and impact/blast-radius tracing so agents answer 'what breaks if I change this?' in a few hundred tokens.

Local-first Windows desktop app: explore your codebase as an interactive dependency graph, semantic search, git context, and optional AI (Groq) for explanations and what-if analysis. SQLite + ChromaDB-no separate DB server.

An intuitive, Google Tag Manager-inspired system to embed, govern, and utilize anchor tags for deterministic agent planning and validation in complex codebases

Repo-native operating layer for AI agents: memory, planning, proof, routing, and continuity across sessions.

Single-binary, blazing-fast code-intelligence engine for AI coding agents — indexes any repo into a queryable structural graph and serves it over MCP, CLI, and JSON with token-budgeted output. No cloud, no DB, no Python.

A cartographer folder: point it at a body of work still in force and it leaves a map a cold reader can wander — catalog, then one card, then stop.

Hierarchical codebase navigation skill for Claude Code / AI coding agents. Generates per-directory CODEMAP.md index files with structure summaries, key exports with source annotations, and large file deep analysis.

A cheat sheet that stops AI agents from scanning your whole repo and saves you tokens.

Codex and Claude Code skill for agent-maintained project wikis, layered code indexes, and low-token repo navigation.

A Claude Code skill that automatically maintains PROJECT.md as a living, human-readable project map. Bilingual (EN/ZH).

Reduce Claude Code token usage 54–67%. MCP server for web engineers — AI agents find symbols, trace callers, and map hierarchies by name instead of reading files. Built for TypeScript. Works with Claude Code, Cursor, and Codex.

Source-first skills and templates for AI-native software development: navigate, structure, and review codebases ｜ 面向 AI 原生软件开发的源码优先技能与模板：导航、组织与审查代码库

A self-updating knowledge graph for your projects — external memory for AI agents.

RepoMap AI 2026: Map Codebases for AI Assistants Beyond Window Limits