Spec Driven Development 🤠 Write codebase-aware specs for AI coding agents so they don't derail.

Wiki-based retrieval for AI coding agents. 65× token reduction, +24pp Coverage@5 on SWE-bench Verified.

Local-first codebase indexing for Claude Code, Codex CLI, OpenCode & AI coding agents — hybrid FTS5 + Tree-sitter + graph search, fully offline.

Codebase indexing

serves for redirect of indexing request. These are problematic when used llama.cpp tries to access /api/embed which is not supported endpoint

Code Graph Builder is a local-first codebase analysis tool with a FastAPI backend and a React frontend. It indexes a repository, builds a navigable code graph and lets you analyze Python and PHP codebases, optionally use Ollama, Open WebUI, or another OpenAI-compatible endpoint for model-assisted graph refinement

Turn any codebase into a navigable Mermaid chart memory system. Human-readable, AI-traversable, works with Claude Code, Cursor, Windsurf, Copilot and any AI assistant.

Atlas is a offline codebase index for LLM coding assistants. Extracts symbols, imports, call graphs, and architecture into a queryable format. Lets AI agents search the index first, then open only the files they need, reducing token overhead and speeding up code navigation. Single-file deployment, zero dependencies.

Automated multi-project codebase indexer for Qdrant. Real-time monitoring and seamless sync for AI agent context.

Scythe (ctx) is a live, auto-updating codebase context engine. It maintains a local SQLite relational graph of your repository, synced dynamically on edit by AI models, guaranteeing structured, zero-drift context under 10k tokens — even for million-line codebases.

Codebase indexing and search tool in command line and Neovim.

An MCP server that exposes the full functionality of Doxygen to AI agents to (1) assist codebase investigation (2) automate documentation generation from source code comments and parse classes, functions, and variables to produce output in XML, HTML, PDF, etc.