Coding agents & developer tools

Codebase search & documentation

1,704 agents · most starred first

Codebase search & documentation, page 7 of 18

claude-code-source-analysis★ 17

拆解 Claude Code|从51万行泄露源码中提炼架构、安全、多Agent设计逻辑,配合13张架构图和正反示例的中文实战手册

Claude-Token-Saver★ 17

Search a codebase in plain words and hand Claude just the functions you need, not whole files. CLI for Windows, macOS and Linux, plus an optional Windows app.

akita-ai★ 16

Your command-line, context-aware chatbot for instant codebase insights & more ✨

context7-auto-research★ 16

Auto-research skill for Context7 - Automatically fetches up-to-date documentation when users ask about libraries and frameworks

prompt-tower.nvim★ 16

⚡ Turn your codebase into AI-ready context in seconds – the Neovim plugin that bridges the gap between your code and AI assistants. Select files, generate structured prompts, and feed your entire project to Claude/ChatGPT/Cursor with zero friction.

githubanalyzer★ 16

AI-powered GitHub profile & repository analyzer with tech stack insights and project health scoring.

gpt-project-context★ 16

Easily provide project context to ChatGPT and boost your productivity with this CLI tool! Scan project files, generate output, and copy it on ChatGPT.

noumenon★ 16

[Discontinued] Knowledge graph for your codebase.

colgrep-agent-2B-GGUF★ 16

transformers gguf code code-search tool-use reinforcement-learning

crewai-code-repo-analyzer★ 15
context-kit★ 15

Generate AI context for your dev stack — works with Claude Code, Cursor, Windsurf, GitHub Copilot, Gemini CLI, or any LLM.

coograph★ 15

Save your tokens!

Automated-readme-generator-with-Multi-Agent-CrewAI★ 15

Fully automated README.md generator powered by multi-agent CREW AI 🤖 and Llama3-70B 🧠—analyzing project structure 📂 and creating custom README styles ✨!

codepicker★ 15

👌🏻 Pick code into Markdown. Apply Markdown to code. Built for LLMs and quick backups.

deepseek-harness-atlas★ 15

针对 [`deepseek-harness`](https://github.com/deepseek-ai/deepseek-harness) 仓库的交互式学习地图:架构分层、依赖脉络、核心流程、模块深读(含**关键源码片段**)、**双源文档库**(官方文档中文优先 + Claude 解读文档)、源码浏览。

SwiftDocAutomator★ 14

SwiftDocAutomator is an AI-powered tool that streamlines the generation of clear and concise documentation comments for Swift code, following Apple and Swift best practices.

ReadMeCreator-With-LLM★ 14

Create informative READMEs effortlessly using AI-driven templates with the README Creator powered by Language Model (LLM). Simplify documentation and enhance project communication.

fnmap★ 14

AI code indexing tool for analyzing JS/TS code structure and generating structured code maps

GithubRepoAgent★ 14

An LLM agent to query any github repo - Ask questions, features, gaps, improvements

myco★ 14

Myco is the nervous system for AI-assisted software teams. Works automatically alongside the coding agents, subagents, and agent teams you already use

codex-harness-internals★ 14

Reverse-engineered specification of the OpenAI Codex CLI harness — agent loop, tools registry, compaction, and context management — as a navigable knowledge graph (1028 rules / 588 structures / 325 use-cases across 18 SRC modules). For agent instruction authors and harness engineers.

watercooler★ 14

Watercooler: your team's shared reasoning layer for agentic coding. Preserve the "why" around your code.

greplm★ 14

Fast, offline code search and code intelligence for LLM agents.

reposkein★ 14

Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust, Go, Java, C#.

openwiki-cc★ 14

Auto-generate and maintain a documentation wiki for any repo — native Claude Code plugin (/openwiki:wiki) & OpenAI Codex skill. A faithful port of OpenWiki: grounds every doc in your source & git history, updates only what changed.

ReCodeAgent★ 14

Artifact repository for the paper "ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories", In Proceedings of The 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026), Munich, Germany, October 2026

codestract-context-tool★ 13

Export the complete contents of your project directory into a context file for LLMs.

github-repo-to-single-file★ 13

TypeScript CLI that pulls a GitHub repo and merges all text-like files into one clean .txt or .pdf. Skips binaries, streams progress, writes to /out. Ideal for LLMs and RAG: feed an entire codebase as a single artifact so models can use the repository context seamlessly.

jqassistant-graph-rag★ 13

Source code graph RAG (graphRAG) for Java/Kotlin development based on jQAssistant

CodeScope★ 13

CodeScope does not understand code. It verifies it. A high-performance code graph engine with MCP protocol for AI agents (Claude/Cursor) to ask "Does the code actually do what you claim?"

pyobfus★ 13

AST-based Python obfuscator with reverse stack-trace mapping — obfuscate before shipping and keep production tracebacks AI-debuggable. MCP + VS Code.

codemium★ 13

Persistent coding intelligence for Codex — project-aware context, adaptive reasoning, scoped changes, and risk-aware verification.

LLMs-Generator★ 12

An agentic solution designed to create a llms.txt file for any given repo or folder.

codeweaver★ 12

Semantic code search for AI agents — 166+ languages, hybrid search, works offline

llamaindex-docs-agent★ 12

A simple ReAct agent that has access to LlamaIndex docs and to the internet to provide you with insights on LlamaIndex itself.

coderag★ 12

Lightning-fast semantic code search with AST chunking (15+ languages) - Hybrid TF-IDF + Vector, MCP-ready for AI assistants

reveal★ 12

Progressive file disclosure for agentic AI - explore files hierarchically with plugin-based analyzers

greppy★ 12

Local code navigation for coding agents: deterministic symbol graph, semantic search, compact briefings, and byte-exact real-grep passthrough. One native Rust binary.

pyvisualizer★ 12

A deterministic, AST-verified call graph for any Python project — every edge traceable to a file:line. The reproducible, CI-gateable alternative to LLM-generated diagrams. No code executed. Nothing leaves your machine.

miru-code★ 12

Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.

codeatlas-platform★ 12

AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec. Analyze any codebase in minutes.

menderbot★ 11

AI-powered command line tool for working with legacy code

CURA★ 11

The official framework for the Code Understanding and Reasoning Agent (CURA)

aisearch★ 11

An AI Code Search Utility Tool with sonnet 3.7 or o4-mini

rescuerepo★ 11

Project for the Bio X AI Hackathon. All about resurrecting old abandonware repos, and reducing the effort to get them up and running again.

func-test-agent-llm★ 11

A LLM agent capable of writing an API documentation and functional tests from a file containing the entrypoints code.

code-scope★ 11

✨ AI-powered code analysis. Analyse your code and unlock its potential.

pagepilot★ 11

PagePilot is a VS Code Chat participant that automatically loads external context (documentation, APIs, README files) to provide enhanced responses. Language is automatically detected from your VS Code settings.

git-semantic★ 11

Semantic grep for codebases — tree-sitter chunking, vector search, shared via Git orphan branch

mastermind★ 11

Local Rust codegraph and verifiable workflow for AI coding agents — project maps, change and test impact, MCP queries, and diff-backed implementation audits.

knot★ 11

High-performance Rust MCP server & CLI codebase indexer for AI agents. Unlocks deep codebase understanding through semantic vector search, structural graph traversal, and cross-repo dependency resolution. Empowers AI coding agents with semantic and structural search for maximum token efficiency.

deepfork★ 11

Don't fork the code. Fork the design. An agent skill that reverse-engineers any open-source repo into a clean explanation + a rebuildable clean-room blueprint — then builds YOUR version. Powered by knowledge graphs.

Synax★ 11

Turn a local codebase into a source-linked, refreshable design wiki that becomes the context layer for agent-assisted development.

hcifootprint★ 11

Turn a web app's interaction surface into a typed, traversable skill graph an LLM can plan over — the frontend sibling of footprintjs.

feynman★ 11

interactive, model checkable specs

deeprepo★ 10

AI project memory for every coding tool. Analyze once, paste anywhere.

Codentis★ 10

Codentis is an AI-powered terminal tool that understands your codebase, analyzes repositories, and helps you explore and work with code faster.

navegador★ 10

AST + knowledge graph context engine for AI coding agents

DotSlash7.0-Githubify★ 10

Understanding any codebase. Enter the github repo's url and chat with the codebase.

notemac-plus-plus★ 10

A powerful Notepad++ inspired text & source code editor for macOS and Web. 73+ languages with Compile & Run, Git integration, AI assistant, hex editor, shortcut presets, terminal, plugins. Built with React, Monaco, TypeScript.

ask-your-stack★ 10

Ask your stack demo

AutoDoc★ 10

Auto documentation - Commits to Reports 📚

context-os★ 10

Claude Code's first turn opens the right file instead of grepping — a local static-analysis repo graph injected before turn 1 (no embeddings/server, MIT). −40.9% tokens on a cold-cache A/B; retrieval quality is CI-gated. Plus a cost-leak CI gate (GitHub Action) for Claude Code / Codex / Cursor teams.

arch-insight★ 10

An agent skill for turning source repositories into architecture insight, design philosophy, tradeoff analysis, and borrowable engineering patterns.

instant-grep★ 10

No longer maintained.

codegraph★ 10

🕸️ Code knowledge graph for Claude Code & AI coding agents — index TypeScript, NestJS, React into Neo4j and query architecture in Cypher

CodeCortex★ 10

Persistent codebase knowledge layer for AI agents. Pre-builds architecture, dependency, coupling, and risk knowledge served via MCP. 27 languages, 13 tools.

repo-wiki-agent★ 10

repo-wiki-agent

chan★ 10

chan monorepo

printing-press★ 10

Agentic First OpenAPI Documentation. Works 100% offline, straight from disk, shareable or publisable to any static host. AI and agent output built in, Built in API Catalog generation.

astro-slop★ 10

The most complete and flexible Astro integration for LLMs and generating markdown versions of pages. Per-page .md siblings, llms.txt index, content negotiation, and link rel=alternate.

loctree★ 10

Structural code intelligence for AI agents. Scan once, query everything — dead exports, circular imports, dependency graphs, and more. CLI + MCP server.

openvisio-oss★ 10
jdbg★ 10

Debug Java like an agent: persistent runtime sessions, safe JDI inspection, jdb fallback, and MCP/CLI control.

ragcode★ 10

Verified, fully-local code context for AI agents. MCP-native. No cloud, no editor lock-in.

lorelum★ 10

Engineering knowledge infrastructure for AI coding agents.

codebase-index★ 10

Local code map for AI coding agents: find, trace, and predict change impact with file:line evidence. Claude Code · Codex · OpenCode · MCP. No network by default.

HoloScript★ 10

A general-purpose semantic systems programming language. Describe a system once; real compilers lower the same source into engine builds, backend services, robots, web runtimes, and headset apps. Not a scripting language.

kortext★ 10

The project brain for AI-driven development: a brief becomes approved analysis documents, then your own agent CLI (Claude, Codex etc.) writes the code. Local-first, no API key of its own.

code-analysis-mcp★ 10

gradio mcp-server-track code-analysis openai anthropic mistral mcp-server region:us

yarramate★ 10

Give your coding agents correct architecture context: design declared once in git, mechanically checked, drift-detected, and rendered into verified briefs

backstory★ 10

Local-first memory for AI-assisted coding. Git shows what changed. Backstory shows why.

ctx★ 10

🧠 ctx is a queryable world model of a codebase, built to ground and govern the language models that modify it

jsunpack-example★ 10

This repository demonstrates the decompilation results of [jsunpack]

eext-chat-with-ai-kimi★ 10

嘉立创EDA专业版扩展:Kimi AI助手,支持查询元件和解析网表。EasyEDA Pro extension: Kimi AI helper to support component query and netlist analysis.

egent-code-plexus★ 10

A high-performance code intelligence graph for LLMs and AI agents. Sub-second structural queries, impact analysis, and cross-repo API contracts for autonomous coding workflows.

prism★ 10

Semantic change intelligence for coding agents — complete impact sets, edit-ready context, and diff verification. Local CLI, MCP, and Go API.

katana★ 10

Source-free architecture maps and deterministic polyglot refactoring for AI coding agents

code-intel-pipeline★ 10

Local code-intelligence pipeline for AI coding agents: architecture maps, hotspots, change impact, and structural regression gates before the agent edits. Rust core, powered by rg + Repowise + Understand + Sentrux.

github-agent★ 10

Browser-native AI assistant for GitHub. Chat with your repositories, search code and review issues from a local app. Your token never leaves the browser and there is no backend.

codegraph★ 10

CLI, MCP and TS library that turns source code into a map of files, symbols, references, and dependencies using tree-sitter.

cortex★ 10

Cortex is a sophisticated AI coding assistant that combines the power of multi-agent orchestration with Retrieval-Augmented Generation (RAG) to provide intelligent, context-aware answers about your codebase. Built with privacy in mind, Cortex runs entirely locally using Ollama or can be configured to use OpenAI's models.

sysml-repo-modeler★ 10

Self-hosted AI analysis harness that turns GitHub repositories into validated SysML v2 and interactive architecture graphs.

doc-bridge★ 10

Portable doc bridge for AI agents — OKF + Self-Describe + AgentHandoff. CLI, MCP, Fumadocs/Docusaurus adapters.

Phantom★ 10

AI-generated animated explanations of code — paste any function, get a cinematic animation of what it does

scanr★ 10

X-ray for TypeScript agents: inventory, refs, slop, dupes. Offline. No API.

kb★ 10

A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.

better-readme★ 10

📝 Audit, generate, and optimize project README files with quality scoring, template matching, and multilingual support

explain-for-dumb★ 10

Claude Code skill that explains code changes in plain human language — no scary jargon. Two modes: a 'for dummies' story or a per-file walkthrough.

Code-Knowledge-Graph★ 10

GKG is Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, OpenCode, and Hermes Agent — to save 💰💲, 🌟 Star if you like it! 🌟

More in Coding agents & developer tools