Coding agents & developer tools

Codebase search & documentation

1,704 agents · most starred first

Codebase search & documentation, page 5 of 18

LSAP★ 45

LSAP (Language Server Agent Protocol) is an open protocol that defines how AI coding agents interact with Language Servers

Reverse-Engineer-Anything★ 45

Guide pédagogique non officiel en français sur REA (Reverse Engineer Anything) : analyser des applications et des binaires avec un agent de code via MCP et CLI, Hopper ou Ghidra, preuves à l'appui. Inclut le cadre légal de la rétro-ingénierie. Projet amont : morluto/rea.

gh_repo_download★ 44

download and view the contents of a GitHub repository or a ZIP file as a single text file

cicada★ 44

AI Coders search blindly. Be their guide.

ontomics★ 44

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.

showsignature★ 44

A CLI that extracts the useful structure from source files: signatures, imports, types, variables, comments, and Markdown sections.

docflow★ 44

Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.

python-code-analyst★ 44

AST-based Python static analysis toolkit for AI agents — complexity metrics, call graphs, dead code detection

dari-docs★ 43

optimize your documentation through fleets of agents

pluck★ 43

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

TZeroAlgorithm★ 43

Deterministic AST Context Compressor & MCP Server for Cursor, Claude & Local LLMs. Cuts prompt tokens by 85–95% with 100% Zero-Leak security.

ziya★ 42

Self-hosted AI technical workbench. Visual, persistent, multi-stream. Development, architecture, and operational analytics without losing context.

beacon-plugin★ 42

Semantic code search plugin for Claude Code using hybrid vector search + BM25. 98% accuracy, 5x faster than grep.

agents★ 42

AI Workflows designed to help manage and update EventCatalog in your CI/CD

CodeDebrief★ 42

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

session-indexer★ 42

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama) with FTS5 fallback.

pi-lsp-extension★ 42

Pi coding agent extension for LSP integration — gives the LLM access to diagnostics, hover, go-to-definition, references, symbols, and rename

rust-porting-playbook★ 42

An extensive agent playbook for automated porting of Python to Rust

code-trace-tree-vscode★ 42

Code Trace Tree is a VS Code/JetBrains plugin that traces code in a tree structure with AI support. Build and display code workflows as trace points. Add traces from the editor menu or the Agent Skill; double-click to jump to the source.

gpt-project-insight★ 41

An engine for generating recursive documentation and using it to work on a project with ChatGPT

fnord★ 41

Fnord is an AI code archaeologist.

codemap★ 41

Codemap generates a compact, token-aware map of a codebase: files, symbols, and markdown structure. Designed for feeding context to LLMs and coding agents.

architecture-catalog★ 41

Git-native architecture catalog — Markdown registry, schema-driven UI, AI-ready

BIM_LLM_code_agent★ 41

BIM LLM Code Agent with Vector and Graph RAG

DevProjex★ 41

Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.

SeeRepo★ 41

LLM Agents Can See Code Repositories [ASE 2026]

e5r★ 41

The Reverse Engineering Toolkit for AI Agents

dsh-lsp-actions★ 41

LSP action surface for DeepSeek Harness: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints, and rename tools over language servers

codebasechat★ 40

Create a GPT chatbot for any GitHub repo in just 30 seconds

booklib★ 40

Detects what your AI doesn't know about your project and fixes it. Post-training gap detection, runtime context injection via MCP.

code_using_GPT★ 39

Analyzing code using GPT .(通过GPT分析代码,增加注释,生成文档)

claude-code-notes★ 39

Claude Code v2.1.88 源码深度分析笔记 — 架构解析 + 面试八股

agent-compass★ 39

Get your repo ready for AI.

colgrep-agent-2B★ 39

transformers safetensors llama text-generation code code-search

srcwalk★ 38

Code navigation for AI agents - exact reads, structural discovery, evidence packets. One binary, zero config.

Annotated-AST-For-LLM★ 38

Annotated AST for the purposes of LLM code repository context. Use this novel approach to pre-process your Github repository. This project will generate an AST.json file which will contextually represent the repo for you to share as a single file to LLM directly or Vector Store

seek★ 38

Ranked local search for AI coding agents. Search the current Git worktree, selected paths, external folders, or exact files. Single binary, no server, no API key.

r-doc★ 38

AI agent skill for maintaining project AGENTS.md and docs/ documentation systems.

hide★ 38

The Turbo Haskell IDE

shrike★ 38

See what your app actually does. Click anything and watch the trip through your code, database and services, with real values. AI-native: your agent sees it too and fixes the real problem.

axon-pro★ 37

Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.

documentor★ 37

Improve technical documentation with the power of AI.

coco-search★ 37

Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.

CodeStory★ 37

CodeStory is a codebase grounding engine that preindexes code into a knowledge graph and enriches it with semantic context. Paired with coding agents, it results in fewer tokens, fewer tool calls, and remains 100% local.

repotracer★ 37

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.

rea-gems★ 37

A curated, auto-updated gallery of excellent reverse-engineering cases built with REA (reverse engineer anything) - refreshed daily by GitHub Actions

jotbot★ 36

JotBot generates the missing code documentation for your Go and TypeScript projects. Powered by AI.

kodyfire★ 35

AI-powered code generator and automation tool

Paper-to-Code★ 35

Paper to Code automates the incorporation of research paper concepts into practical code using OpenAI's GPT models, bridging theory and implementation.

shebe★ 35

Fast BM25 full-text search for code repositories with MCP integration for AI coding agents.

agent-ready★ 35

Codebase readiness scoring for autonomous agents — measurable operability standards beyond instructions.

remembrallmcp★ 35

Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.

Lossless-Codex-Orchestrator-LCO★ 35

Index, search, summarize, and approval-gate local Codex sessions through OpenClaw/MCP. Agent-first recall and dry-run orchestration for Codex-heavy work.

sourceant★ 35

Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.

repowiki★ 35

Deterministic repo-wiki build system, driven by any coding agent. Zero LLM, zero network.

gptree-gui★ 34

A tool to provide LLM context for coding projects by combining project files into a single text file (or clipboard text) with directory tree structure.

DraCo★ 34

Dataflow-guided retrieval augmentation for repository-level code completion, ACL 2024 (main)

mcp-adr-analysis-server★ 34

Your ADRs are lying to you. MCP server with live drift detection, content safety, and decision memory — validates architectural decisions against your actual code.

wikigen★ 34

Generate GitHub Wiki from source code using Claude Code. Single Go binary, no Docker needed.

mneme★ 34

Architectural drift prevention for the agentic AI SDLC.

codesearch★ 33

Semantic Code Search tool. Query your codebases using natural language

create_pg_super_document★ 33

create_pg_super_document is a project that generates documentation for all symbols in the PostgreSQL codebase, then utilizes these symbol documents to create high-quality documentation for functionalities, components, and other elements using AI agents

NITR★ 33

Needle in the Repo (NITR) dataset for maintainability issues in AI generated repository edits

grasp★ 33

GRASP — Code architecture visualizer + 150-tool MCP server. Dependency graphs, security scanning, multimodal knowledge graph, ORM tracking, git change impact, graph schema v3. Works with GitHub, GitLab & local dirs. 35 languages. Zero data collection.

GitHub-Stars-AI-Tools★ 33

本地优先的 GitHub Stars AI 桌面应用,用于同步、摘要、标签、搜索和发现项目。Local-first AI desktop app for GitHub Stars.

TeaRAGs-MCP★ 33

The Codebase Intelligence layer for AI coding agents. Semantic indexing, graph navigation, and repository intelligence

DbgGPT★ 32

🏀 DbgGPT - my first basic x64dbg/openai plugin

scope★ 32

Structural code intelligence for LLM coding agents. Agents that understand the architecture finish in fewer turns. Fewer turns = less cache accumulation = lower cost. Benchmarked: 32% cheaper agent sessions.

learn-claude-code★ 32

Learn Claude Code — 基于源码的完整技术分析文档集,15章深度解析 Agent Loop、工具系统、权限系统等核心机制

docs★ 31

This is the documentation for Kilo Code, open source AI coding assistant for planning, building, and fixing code.

code-index★ 31

Self-hosted semantic code search platform — Go server with web dashboard, CLI, and AI-agent skills. Search code by meaning, not text: hybrid BM25 + dense embeddings via llama.cpp.

nerfify-code★ 31

[CVPR 2026 Highlight] Offical code for- NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code

sema★ 31

Local semantic code index and MCP server for Claude Code, Codex, and opencode. Includes semantic search, reuse checks, impact analysis, and a VS Code chat and agent supporting local CLIs and API providers—all powered by tree-sitter, SBERT, and ChromaDB.

supergrep★ 31

Retrieval + inference offload for AI coding agents.

Yagent★ 31

Vim style TUI with Repository-Aware, Self-Evolving Agent That Understands Codebase in Real Time powered by Hybrid Semantic + Full-Text Engine

rgctl★ 31

A code knowledge graph built for LLM agents — accurate answers, minimal tokens, maximum speed

cortex★ 30

Code graph tool for AI assistants - understand codebase structure, dependencies, and impact

ContextAtlas★ 30

ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector search, FTS5 and token-aware context packing.

typo3-solver★ 30

💡 Extension for TYPO3 CMS to extend TYPO3's exception handling with AI generated solutions.

atcode★ 30

AI code knowledge graph for code understanding, graph retrieval, and agent workflows

codeactor-agent★ 30

Vim style TUI with Repository-Aware, Self-Evolving Agent That Understands Codebase in Real Time powered by Hybrid Semantic + Full-Text Engine

rekipedia★ 30

Turn your codebase into readable format, for both Human and AI Agent.

Claude-code-research★ 30

Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告,7种语言

GraphFlow★ 30

Local-first code knowledge graph and context harness for coding agents. MCP + DeepSeek Harness (dsh) plugin.

codectx★ 29

Codebase context compiler for AI agents. Graph-ranked, token-budgeted, tier-compressed output. Smarter than the existing ones.

AutoGen★ 29

Auto generate anything

called★ 29

Analyzer: called is a analyzer which can find function calling

tutorial-any-repo★ 29

Claude Code skill: Generate file-by-file code tutorial websites for any repository with parallel agent teams

excod★ 29

A tool that scans a codebase, pick the important files, and export them as JSON to your clipboard or a file.

aming-claw★ 29

Shared workspace for AI agents and human developers. See, audit, and review every change AI makes to your codebase. Multi-language graph (Python/TypeScript), MCP-native, local-first.

threadnote★ 29

Local-first engineering memory and large-scale polyglot graph search for Codex, Claude, Cursor, Copilot, and the next agent you try.

clonar-programa★ 29

Guia e skill para clonar sites, apps desktop e mobile com método: evidência, arquitetura, spec, implementação própria e paridade.

commentator★ 28

Automatically comments Python code, adding docstrings and type annotations, with optional translation to other languages.

claude-code-sourcemap★ 28

The sourcemap of claude code, the best coding agent of the world

h-codex★ 28

A semantic code search tool for intelligent, cross-repo context retrieval.

CodeRAG★ 28

Advanced graph-based code analysis for AI-assisted software development

contextd★ 28

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

surface★ 28

Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it fails the build when the code a doc describes changes. Deterministic, no LLM.

codescout★ 28

High-performance coding agent toolkit MCP server — IDE-grade code intelligence for LLMs

EKOS★ 28

EKOS is an AI-native platform that continuously reconstructs, compiles, stores and serves enterprise knowledge.

More in Coding agents & developer tools