Coding agents & developer tools

Codebase search & documentation

1,704 agents · most starred first

Codebase search & documentation, page 6 of 18

symbolgraph★ 28

Local-first code intelligence for AI agents — tree-sitter symbol graphs and hybrid (FTS5 + vector + graph) retrieval via CLI and MCP server.

chatpdb★ 27

Chat with your Python debugger

codegraph-cli★ 27

AI-powered code intelligence CLI with multi-agent analysis, impact graphs, and conversational coding.

RepoBrain★ 27

Local codebase indexing and search tool. Supports hybrid search, flow tracing and impact analysis.

openbrep★ 27

OpenBrep — 面向 ArchiCAD 高阶用户和 GDL 开发者的 AI 工作台。编译验证、知识驱动、资产可追溯

rtfm★ 27

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 24 parsers (incl. EPUB, DOCX, ODT, MIDI, audio), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.

data2prompt★ 27

Data2prompt is a powerful OSS CLI tool that compiles your entire data-heavy project into a single AI-optimized file. Handles CSVs, Excel, SQLite & notebooks like data, not raw text dumps. data2prompt fits into the Context Engineering phase of the data science lifecycle, bridging the gap between local development and LLM reasoning.

metatron★ 27

Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer.

duvlify★ 27

Beautiful docs for humans. Native tools for agents. An open-source Astro framework for documentation you own end to end: Markdown in, static site with search, an API reference and an MCP server out.

Engineering-Code-Analysis★ 26

Automated and fast parsing of local project directories and GitHub directories, one-click deployment of local parsing with AutoGPT(自动化快速解析本地工程目录和github目录,一键部署本地解析AutoGPT)

provenant★ 26

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

harness-engineering-ko★ 26

Korean translation of "Harness Engineering: From Claude Code Internals to AI Coding Best Practices" — Claude Code 소스 코드를 체계적으로 분석하여 AI Agent 시스템의 핵심 엔지니어링 패턴을 추출한 기술서의 한국어

Repo-Sage★ 26

An autonomous, 100% local Agentic GraphRAG system for codebase intelligence. Paste any GitHub URL or local directory to chat with your code. Powered by LangGraph, NetworkX, and Ollama (qwen2.5-coder).

recurse★ 26

Cursor for Reverse Engineering

agentpack★ 26

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.

context-mcp-subgraph★ 26

MCP-based code knowledge graph and budgeted context subgraph retrieval for AI coding agents.

fm-lab★ 26

Open Source framework for agentic FileMaker development. Turns SaXML exports into a fast DuckDB-powered digital twin for analysis, documentation, and AI-assisted coding.

sage★ 25

AI copilot designed to enhance developer productivity and streamline onboarding processes

ai-context-optimization★ 25

Techniques and tools for optimizing how AI coding assistants understand your codebase, with a focus on cost reduction and efficiency.

SWAGENT★ 25

API Documentation for the Agent Era

hypergrep★ 25

A better grep for AI agents. Structural search, call graphs, impact analysis, semantic compression. 87% fewer tokens. 16 languages. Built in Rust.

docguard★ 25

The enforcement tool for Canonical-Driven Development (CDD). Audit, generate, and guard your project documentation. Zero dependencies.

AI-Code-Analyzer★ 25

An intelligent code analysis system powered by AI large language models that automatically generates project summaries, tech stack analysis, architecture design, implementation principles, and produces Mermaid visualizations (architecture diagrams, flowcharts, class diagrams, sequence diagrams, etc.). Supports real-time streaming AI output with Mar

building-blocks★ 25

A living standard for a web stack that AI agents can verify, not just generate

repo-canvas★ 25

Local semantic project map with live agent work and session navigation

bonsai-ninja★ 25

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

HoloGram★ 25

3D code dependency graph generator with built-in LLM agent. Language-agnostic (Python, TypeScript, Rust, Go, Java, C/C++, C#, Ruby, Kotlin, Swift, PHP, Lua). Coupling depth analysis, constraint gating, real-time file watching. Tauri 2 + Three.js + Rust engine.跨语言代码依赖拓扑图生成器 · 14 门语言统一 IR · 3D 全息星图 · 内置 AI Agent 双向联动 · 四级耦合诊断 · 桌面应用 / CLI 双模

rag-rat★ 25

Local repo-intelligence index + MCP server: semantic search, symbol/graph navigation, impact-surface preflight, git + GitHub papertrail, and a source-anchored memory graph.

mcpp-language-server★ 25

mcppls — a C++20/23 modules language server: one set of module semantics on GCC, Clang, MSVC and MinGW, for editors (VS Code, Zed, CLion, Neovim), AI Agents (MCP) and CI

adrkit★ 25

Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, and MCP.

rgctl★ 25

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

vibesequence★ 25

Living docs for you and your AI assistant. VibeSequence reads your code and draws every route, command and handler as a zoomable sequence diagram.

grand-tour-rpocket★ 25

Agent skill that conducts an interactive architectural walkthrough and verification quiz over a codebase.

chatgithub★ 24

Exploring GitHub Using Natural Language built with OpenAI Functions and Vercel AI SDK.

RepoLingo★ 24

RepoLingo -Turn any GitHub Repository into LLM-ready data.

Contextinator★ 24

Turning messy repos into weapons of mass structured context.

m1nd★ 24

m1nd is a local-first context runtime for coding agents: an evidence-bound, continuously verified model of your code, memory, and change.

codebase-knowledge-builder★ 24

Portable Agent Skill for codebase understanding and developer onboarding, producing source-cited Markdown artifacts with architecture, flows, error paths, and unknowns.

knowing★ 24

Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.

senior-architect-agent★ 24

Senior Architect Agent: AI architecture skill for existing system mapping, software architecture documentation, Mermaid diagrams, and AI agent handoff.

bifrost★ 24

Multi-language static analysis for agents, editors, and large repositories.

gitcontribute★ 24

Contribution research for agents: check repository guidance, related work, code context, and validation before writing a patch.

slcr★ 24

An open standard for agent-native software requirements.

interfazzle★ 23

A Swift CLI tool for building simple Markdown docs for a package's public interface from its symbol graphs. LLMs love that stuff, too!

statGPT★ 23

Simple plugin to instantly transform broken English into working code and analysis in RStudio using Open AI's API

Mapr★ 23

Mapr is a Bun-native CLI/TUI designed for deep frontend reverse-engineering. It crawls target sites to collect artifacts, processes chunked code through a multi-agent AI pipeline, and generates comprehensive Markdown reports—mapping initialization flows, restoring names, and inferring call graphs to simplify complex build outputs.

project-to-markdown★ 23

Project To Markdown: Project files into structured markdown, optimizing documentation for AI analysis. Enhances AI assistants' performance in understanding project context, featuring both GUI and CLI interfaces. Ideal for improving AI-powered code comprehension and problem-solving.

company-brain★ 23

Template for creating a long-term sync hub that checks your company's data sources into Git as plain Markdown, giving AI coding agents durable, greppable context about your business.

CodeContext★ 23

CLI tool & MCP server that turns a codebase into text for an LLM to see its context — feed code to ChatGPT, Claude, or any AI coding assistant

codegraph-rust★ 23

Deterministic tree-sitter + SQLite/FTS5 code knowledge graph for coding agents and developers: symbols, calls and dependencies over a CLI, an MCP server and a local browser viewer. No AI/LLM inside; byte-stable output.

idalib-cli★ 23

A IDA CLI tool built on Rust, idalib-rs, and idalib. Supports batch and concurrent IDA analysis processes, design for stateless, agent first, skill first, and automation first. Reduce AI understanding and friction costs, make agents to efficiently execute complex binary analysis tasks.

fpga-project-analyzer★ 23

See and review any Vivado / Zynq / PYNQ project: drill-down Vivado-style diagrams and clock-domain, constraint and overlay checks for AI coding agents.

ctx3★ 22

Context Tree is a code analysis cli tool written in Go that helps you and LLMs to understand a codebase/project better!

amdb★ 22

Give your AI Agent understanding of your codebase. A Rust CLI that turns your entire project into a single, optimized context file for Cursor, Antigravity, and Claude.

decode-claude-code-analysis★ 22

Claude Code v2.1.88 architecture deep dive — 12 chapters, 8,400+ lines of analysis | Claude Code v2.1.88 架构深度解析 — 12 章,8,400+ 行深度分析

xgrep★ 22

Ultra-fast indexed code search engine — faster than ripgrep on repeated searches, lighter than zoekt. Built-in MCP server for AI agents. Also does fast file finding (fd/find alternative).

costwise-mcp★ 22

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.

Delphi-RAG-Lint★ 22

Delphi code index + linter + refactorer for RAD Studio, VS Code and AI assistants (CLI, LSP, MCP). 423 lint rules. Pure Delphi, no cloud AI. Alpha.

opcore★ 22

The robustness engine for AI coding agents. A local Rust code graph gives an agent repo-wide understanding, a validation gate that runs before an edit lands, and safe symbol-aware edits. Deep on TypeScript, useful on Rust, local and deterministic.

FixMap★ 22

Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.

seemore★ 22

Zero config documentation tool - Let AI write the Markdown. Let seemore show it better.

codiluce★ 22

See how your code fits together, even as agents keep changing it. A zoomable, evidenced map of your repository: every flow, its Git history and blast radius, explained over MCP.

srag★ 21

Semantic code search and RAG system written in Rust with tree-sitter chunking, MCP server for IDE integration, prompt injection detection, and secret redaction

GitArch★ 21

Generate interactive reports from any GitHub repository with summaries, architecture diagrams, and code insights

codebased★ 21

Embedded AI search engine for code

phenixcode★ 21

Privacy-focused, self-hosted RAG assistant for querying codebases with local or cloud LLMs.

llms-txt-generator★ 21

The ultimate AI-powered generator for llms.txt and llms-full.txt files.

AI-Code-Converter★ 21

This web application allows you to convert code from one programming language to another using the ChatGPT API. It also provides code debugging and code quality checking features.

sgrep★ 21

semantic grep

agentic-codebase★ 21

Semantic code intelligence for AI agents — compile repositories into navigable concept graphs with impact analysis, coupling detection, and prophecy.

codesage★ 21

Code intelligence engine for AI coding agents. Structural graph queries plus semantic search, exposed via CLI and MCP.

neat★ 21

Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real full-stack context.

gptdoc★ 20

Generate documentation comments with OpenAI models.

base44-docs-tool★ 20

Instant, local access to complete Base44 documentation with AI assistant integration

repolens★ 20

Catch tech debt and hidden risks before they become incidents. Add m in front of github.com/user/repo to find functions and trace the logic.

cartog★ 20

Pre-indexed code knowledge graph via treesitter, enchanced query with RAG, MCP server, private and local storage. Agent ready.

RepoDoc★ 20

RepoDoc is a lightweight, zero-dependency utility that scans any project directory and generates a complete Markdown document containing the full directory structure and source code of all text-based files.

Reflexia★ 19

Autodoc project, aimed to autonomously generating documentation for any code repository and store info about it in vectorstore to further interactions

VerilogAI★ 19

VerilogAI – A specialized chatbot for Verilog. Supports code generation, debugging, and explanation with custom prompt engineering and API backend.

dsl-xpert★ 19

This tool provides a web interface to define domain-specific languages and uses large language models (LLM) to interact with those grammars via chat.

flex★ 19

coding agent session search in sql

STE-Code★ 19

Simplified Technical English for Code - extract, adapt, and enforce ASD-STE100 rules for software documentation. 9-agent pipeline, 59-test benchmark (96.6%), multi-language scaffolding.

ax★ 19

Score any site's agent readiness from your terminal or CI. The open-source CLI for ora.

ImHex-Plugin-Oracle★ 18

A ImHex plugin to ask the almighty Oracle (OpenAI's Davinci AI) for help identifying file formats

osfit★ 18

Turn any GitHub file or issue into clear, multilingual insights instantly. This standalone AI actor explains complex code with flowcharts and generates step-by-step solution plans for issues all in your preferred language.

rephole★ 18

RAG-powered code search via simple REST API

architecture-doc-generator★ 18

AI-powered architecture documentation generator with RAG, hybrid retrieval (semantic + structural), and multi-agent workflows using LangChain

CircuitMind★ 18

The code about TC-Bench and CircuitMind

gosymdb★ 18

A Go symbol and call-graph database backed by SQLite. Query symbols, callers, callees, blast radius, dead code, and interface implementors as structured JSON — typed code navigation for AI agents (MCP) and humans.

cqs★ 18

Code intelligence and RAG for AI agents. Semantic search, call graphs, impact analysis, smart context assembly - in single tool calls. 54 languages + PLC exports. 69.8% R@5 / 43.6% R@1 on dual-judge code-search eval. Daemon mode (3-19ms). MCP server, 30 read tools, full schemas. Local-first, GPU-accelerated.

code-graph-context★ 18

A Model Context Protocol (MCP) server that builds rich code graphs to provide deep contextual understanding of TypeScript codebases to Large Language Models.

dsh-plugin-codegraph★ 18

Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, and what a change reaches, from a tree-sitter index it builds itself. Compatible with the codegraph CLI's on-disk format.

eulix★ 18

Local-first code navigation for large codebases. Parse, index, search, and understand millions of lines of code using structural and semantic retrieval.

copyright-forge-skill★ 18

软件著作权申请材料生成 Skill|Generate standardized software copyright registration materials with AI.

Graph-Hub★ 17

Local-first code intelligence for AI agents. Transform your codebase into a queryable knowledge graph. 85% token savings for Claude Code, Cursor, and MCP-compatible tools.

chatbot★ 17

The project's aim is to develop a chatbot that can help people create spec documents without knowing the specification.To get started with, the bot will consume the spec, JSON schema and serves the user as an expert. So based on a set of questions and answers it will generate an AsyncApi spec document according to the use cases.

amalgo★ 17

CLI tool for creating single-file snapshots of multiple (code) files.

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

agentsmith-cli★ 17

Agentify any repository in one command. AgentSmith maps a local codebase or GitHub URL and generates a Copilot-native engineering team with a root orchestrator, specialist agents, source-backed skills, handoffs, instructions, and optional AgentHub coordination.

github-smart-agent★ 17

AI-powered GitHub repository analyzer that ingests full codebases, enables codebase-wide chat, detects bugs, and suggests optimizations using RAG (LangChain + FAISS + OpenRouter) with a Streamlit UI.

More in Coding agents & developer tools