Coding agents & developer tools

Codebase search & documentation

Codebase search and documentation projects turn a repository into context an AI can actually use. Some build a queryable knowledge graph of code, docs, and schemas, as graphify does, while others like repomix pack a whole repo into a single file for feeding to a model. The difference is whether they index for ongoing search or bundle once for a prompt.

1,704 agents · most starred first

Top 100 of 1,704

graphify★ 150,869

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

Understand-Anything★ 93,400

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

codegraph★ 78,210

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

context7★ 65,163

Context7 Platform -- Up-to-date docs for AI agents

codebase-memory-mcp★ 48,911

Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.

GitNexus★ 47,142

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or ZIP file, and get an interactive knowledge graph with a built in Graph RAG Agent. Perfect for code exploration

serena★ 31,552

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

repomix★ 29,350

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

deepwiki-open★ 18,464

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

openwiki★ 18,037

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

PocketFlow-Tutorial-Codebase-Knowledge★ 12,767

Pocket Flow: Codebase to Tutorial

claude-context★ 12,710

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

Trail-Code★ 11,351

One shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up where you left off.

fff★ 11,243

The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS

bloop★ 9,472

bloop is a fast code search engine written in Rust.

Graft★ 9,335

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

semble★ 6,460

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

potpie★ 5,798

Context Graph for AI Native SDLC

code-graph-rag★ 5,394

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

floorplan★ 5,382

See how your app actually fits together. An interactive, plain-English map of your codebase, drawn by Claude or Codex.

Graft★ 4,663

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

sourcebot★ 4,036

Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.

how-claude-code-works★ 3,840

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码:架构、Agent 循环、上下文工程、工具系统等

adrenaline★ 3,733

Chat with (and visualize) your codebase

sem★ 3,459

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.

SocratiCode★ 3,382

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

lsp-ai★ 3,217

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

deepwiki-rs★ 3,179

Turn code into clarity. Generate accurate technical docs and AI-ready context in minutes—perfectly structured for human teams and intelligent agents.

opensrc★ 3,040

Fetch source code for npm packages to give AI coding agents deeper context

claude-code-from-source★ 3,016

Architecture, patterns & internals of Anthropic's AI coding agent — reverse-engineered from source maps

readme-ai★ 3,013

README file generator, powered by AI.

eventcatalog★ 2,973

The docs platform designed for software architecture. Document your domains, services, events and schemas — for your teams and your AI agents.

jcodemunch-mcp★ 2,858

Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.

aoci-code★ 2,734

A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.

cocoindex-code★ 2,695

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

ripwire★ 2,556

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.

gortex★ 2,089

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d

reversa★ 1,998

Transform legacy systems into executable specifications for AI coding agents

ua-parser★ 1,960

A multi-language port of Browserscope's user agent parser.

grepai★ 1,954

Semantic Search & Call Graphs for AI Agents (100% Local)

blume★ 1,844

The open-source docs framework for humans and agents.

repo2txt★ 1,839

Web-based tool converts GitHub repository contents into a single formatted text file

SolidGPT★ 1,795

Developer AI Persona Search Agent

Claude-Code-Source-Study★ 1,742

Deep dive into Claude Code's source code— learn from the best agent implementation out there.

perf-map-agent★ 1,703

A java agent to generate method mappings to use with the linux `perf` tool

claude-reviews-claude★ 1,647

Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

dox★ 1,511

Self-documenting AGENTS.md

codesight★ 1,425

Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.

repobrain★ 1,363

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

antigravity-workspace-template★ 1,294

Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A with file paths and line numbers. Works in any AI IDE.

sage★ 1,263

Chat with any codebase in under two minutes | Fully local or via third-party APIs

coding_agent_session_search★ 1,220

Unified TUI and CLI to index and search your local coding agent session history across 30+ providers (Codex, Claude Code, Gemini, Cursor, Aider, Copilot, and more) into one searchable timeline. Hybrid search plus robot/JSON output for agents.

ctx★ 1,185

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

Prometheus★ 1,127

🧠 Prometheus: A Knowledge-Graph-Driven 🤖 AI Agent that maps 🗺, understands 🧩, and repairs 🛠 complex codebases — not by guessing, but by reasoning. ⚡

RepoAgent★ 1,059

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

GrapeRoot★ 1,050

Compounding Context for AI Coding Assistants — MCP graph engine for Claude Code, Cursor, Copilot, Gemini, OpenCode

repoprompt-ce★ 997

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

SeeCode★ 991

Animated, explorable diagrams for Claude and other coding agents, from a short JSON spec.

octocode★ 966

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

DeepGit★ 928

Deep research agent to help you find the best GitHub repositories 🕵️!

codegraph-rust★ 917

100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management

llm-ls★ 887

LSP server leveraging LLMs for code completion (and more?)

VectorCode★ 875

A code repository indexing tool to supercharge your LLM experience.

claude-replay★ 863

Convert AI coding agent sessions (Claude Code, Cursor, Codex, Gemini, OpenCode, Kimi Code, Hermes) into self-contained, embeddable HTML replays

ai-doc-gen★ 771

AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.

codeseek★ 762

Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.

axiomcodegraph★ 755

Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.

codemap★ 717

a project brain for your AI. Give LLMs instant architectural context without burning tokens

axon★ 706

Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.

DevoxxGenieIDEAPlugin★ 695

DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development with CLI Runners.

shotgun★ 671

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

sigmap★ 652

~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

build-code-agent★ 644

从零构建 Code Agent:Claude Code 源码深度解析 | Build a Code Agent from Scratch: Deep Dive into Claude Code Source

LocAgent★ 642

[ACL 2025] Graph-guided agentic framework for code localization https://arxiv.org/abs/2503.09089

autopilot★ 608

Code Autopilot, a tool that uses GPT to read a codebase, create context and solve tasks.

Claude-ast-index-search★ 600

Cli allows AST search, ~40-50% economy tokens. Claude/Codex/Cursor searches (suitable for any AI agent that can use Bash)

bugbug★ 580

Platform for Machine Learning projects on Software Engineering

MisakaNet★ 565

Re-debugging Solved Failures? No Way. 1000+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

decomp.wtf★ 556

What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally.

Mantic.sh★ 553

A structural code search engine for Al agents.

real-world-rails★ 545

200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns.

octocode★ 526

Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.

open-docs★ 520

This repository contains documentation created to better understand the open project

roam-code★ 517

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 288 commands, 259 MCP tools, change-safety gates, audit evidence, zero API keys.

Agent-Cockpit★ 515

Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時,每個結論都能追到產生它的程式碼。Claude Code · Codex · Cursor · Gemini CLI

swagger-autogen★ 507

This module performs automatic construction of Swagger documentation. It can identify the endpoints and automatically capture methods such as get, post, put, and so on. It also identifies paths, routes, middlewares, response status codes and parameters. At the end, it generates the .json file containing the Swagger format specification.

repo-analyzer★ 500

AI coding agent skill for deep architectural analysis of open-source projects | 开源项目深度架构分析,一句话生成专业级分析报告

sdl-mcp★ 500

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

ProjectAtlas★ 499

Every file not opened. Every folder not explored. Tokens saved. A local repository map for coding agents: purposes, source, symbols, and dependencies. Native Rust CLI and MCP, isolated worktrees, and subagent hooks.

open-aware★ 496

Aware - Deep Code Research Agent for Complex Codebase & Knowledge that “Act As Your Agentic Principal Engineer”

groma.md★ 492

groma.md - Your architecture as OKF Markdown in Git, and one C4 map you can walk. Scanned from source, curated by you and your agents.

kuna★ 490

An agent-first decompiler designed to be refined by other agents. Kuna is written in Rust and was originally ported from Ghidra.

codeqai★ 488

Local first semantic code search and chat | Leverage custom copilots with fine-tuning datasets from code in Alpaca, Conversational, Completion and Instruction format

docfork★ 483

Docfork - Up-to-date docs for AI Coding Agents.

llmdoc★ 483

TokenRoll LLMDoc for Coding Agent

system-atlas★ 472

An agent skill that turns an architecture discussion into an explorable isometric atlas: one data file, an interactive map and a generated SYSTEM.md

code-context-engine★ 466

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

DocAgent★ 457

DocAgent is a system designed to generate high-quality, context-aware code documentation for Python codebases using a multi-agent approach and hierarchical processing.

context★ 446

Local-first documentation for AI agents

marimo-pair★ 435

Drop agents inside running marimo notebook sessions

More in Coding agents & developer tools