Coding agents & developer tools
Codebase search & documentation
1,704 agents · most starred first
Codebase search & documentation, page 11 of 18
Replicate any Software (Opensource) 🌟 Star if you like it! 🌟
open source reverse engineering toolkit. give it a url, get a reconstruction plan.
Local session indexing and cross-agent work continuity for AI coding assistants. One local index over Codex, Claude Code, ZCode, DSH, Grok, Cursor, Antigravity and Kiro — search, cross-agent timelines, WorkThread continuity, context handoff. No cloud, no telemetry.
Repository-wide code index for LLM prompt context
Official Jamdesk documentation — guides, API reference, components, and tutorials for the Jamdesk documentation platform
Jamdesk CLI — build, preview, and deploy documentation sites from MDX. 50+ components, OpenAPI, AI search, Mintlify migration
lsp-agent is a language server that serves as a backend for AI-powered functionality in your favorite code editors. It offers features like in-editor chatting with LLMs and code completions.
Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a deterministic Elixir semantic graph and agent-ready Repo Map for LLMs.
ProbeCode: AI coding agent integrating static code inspection with a ReAct framework to understand and memorize long-context code.
An Autonomous Multi-Agent Framework for Self-Healing Documentation & Code Optimization
README First: a lightweight context protocol for AI agent collaboration in software projects
Grimoire (gʀiˈmwaːʀ), a book (tool) of magical knowledge about your code and its dependencies.
Merkle-enhanced codebase mapping for AI agents. O(1) change detection, zero-token staleness prevention.
LLM agent for helping all things your codebase
The Developer's Micro-OS — Context management, semantic search, and AI-powered browsing for software engineers.
A CLI written in Java language that generate API interface document and UML diagrams for you using ChatGPT AI.
This project is a Python application that provides an interface for interacting with the GitHub API. The project structure is organized into modules that make it easier to maintain and expand its functionality.
Embeds your codebase into a local vector database and exposes it as an MCP tool for fast semantic code search.
Think of ducky as your over-the-shoulder mentor. He watches your codebase and notifies you when you implement bad code. Ducky helps developers to understand code without handing them the complete answer.
Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli
Semantic codebase understanding service — maps application structure, authentication patterns, authorization models, and data flows for intelligent security analysis.
An AI Expert for your C# Codebase
A simple tool to ingest code files into a single text file for LLM context.
Artifactor — Code intelligence platform. Builds a programmable Intelligence Model from any codebase, queryable by AI agents, your team, or your own tooling.
ISC-CodeConnect is a sophisticated multi-agent Retrieval-Augmented Generation (RAG) system specifically designed for Salesforce development. Built with LangGraph and powered by IBM WatsonX.ai Granite models, it orchestrates a network of specialized AI agents .
Semantic fingerprints for token-efficient and fast code search.
A custom 16-bit Single-Cycle Vector Processor (SIMD) implemented in Verilog. Features a 4-lane parallel architecture, custom 20-bit ISA, and a complete software ecosystem including a Python Assembler and an AI-powered documentation assistant.
Gitra is a self-hosted web app to explore, analyze, and "chat" with any public GitHub repository. It bundles codebases into LLM-optimized context for instant AI analysis using Google Gemini.
React Recall makes it really easy for you and your AI Agents to read logs, trace flows, and recreate / fix bugs.
Generate a VitePress docs site from your codebase with Claude or Codex, then keep it current with bounded in-place updates and internal link checking.
Enhanced fork of claude-context with stability fixes, improved sync, and better reliability for semantic code search
Persistent code graph for AI agents. Tree-sitter → SQLite → MCP. Agents store understanding once, skip re-reads forever. 51–1500x fewer tokens.
Hammy is a code base mapping tool that lets agents talk to your code in a way they understand with an AST, call graph, and VCS history.
macOS developer tool that snapshots your project into one readable file and applies AI-edited changes back. Deterministic, LLM-friendly dump/undump.
Semantic code context for AI agents.
Build and maintain a living knowledge base for any software project. Documents existing code, updates incrementally, audits drift, and never modifies source code. 100% read-only.
Documentation compiler built end-to-end by autonomous Claude Code agents
Audit, optimize, and prepare your Laravel codebase for AI coding agents. Readiness scoring, auto-fixes, AGENTS.md generation, simulation mode, and plugin system.
Open-source ADR orchestrator — explores your codebase, proposes approaches, writes Architecture Decision Records automatically
Agentic, build-validated C# code examples for Aspose.BarCode for .NET covering barcode generation, recognition, and configuration across 60+ symbology's. Includes an agents.md guide for AI coding agents.
An AI-powered Semantic Code Search Engine that lets you query codebases using natural language instead of exact keywords. Built with a high-performance Bun/Hono backend, Next.js, and Qdrant vector embeddings for real-time streaming.
基于java版本的codgraph—— 对中文友好的AI 编码助手(Claude、Cursor、Trae)提供精准代码上下文。基于 Tree-sitter 解析 + SQLite 存储 + MCP 协议,原生感知 Spring Boot / Dubbo / OpenFeign 框架
gradio smolagents agent smolagent tool agent-course region:us
gradio documentation code-assistant large-language-model fire-works-ai region:us
streamlit region:us
gradio region:us
gradio leaderboard region:us
AST-powered codebase indexer skill for coding agents. Spelunk parses repositories with Tree-sitter into a local SQLite index so agents trace dependency trees and locate symbols in under 100ms instead of scanning raw files. Reduces token consumption by up to 90% with instant symbol resolution.
Agentic CLI tool for investigating bugs using code and logs.
Gives LLMs precise answers from pre-researched code across repositories and languages - instead of re-scanning files and rebuilding context every session
Local, explainable context compiler for AI coding agents. Analyze → plan → emit optimal context — with why/doctor diagnostics. No embeddings, no server.
一个面向编程学习、面试准备和 AI 问答场景的springboot+langchain4j项目,在开源项目基础上优化并添加功能:https://github.com/liyupi/ai-code-helper 在此感谢作者开源对我的帮助。
This project is a RAG-based AI chat application using LangChain and OpenAI, featuring codebase analysis and a hierarchical file structure visualization for GitHub repositories.
AI-powered codebase intelligence platform replacing vector chunking with Vectorless RAG via AST graph traversal. Features multi-agent LangGraph workflows, interactive Neo4j NVL graph visualizer, 3-hop blast radius analysis, and automated architectural PDF report generation.
x2fromx - Convert project structures between directories and text trees. InOneClick!
Context Excavator solves a real problem: when you paste large codebases into ChatGPT, the AI gets lost in noise. You're feeding it 500 lines of code when only 20 lines actually matter. The LLM can't tell the difference, so it gives irrelevant answers. This project extracts only the code that matters, automatically..
Auto generation of UniFi network documentation
Git-native structural memory for AI coding agents. Index once — stays fresh on every pull, merge, and branch switch. MCP server for Claude Code, Cursor & any agent.
An LLM-powered repository agent for wiki-style documentation and deep codebase understanding
Static code analyzer for any repository — classify codebase, extract HTTP routes, detect tech stack, map dependency graph. Multi-language (Python, JS, Java, Go, Ruby, PHP). Zero dependencies. Optional LLM enrichment
Web-based AI agent that automatically generates full professional documentation README files for any GitHub repository using local AI models.
An open-source, AI-powered application using Agentic CAG to chat with any public GitHub repository or developer profile, offering deep code analysis, visual architecture maps and security audits.
AISMM (AI-driven Software Meta-Model) is a structured, machine-readable and human-readable way to describe a software product as a complete system.
AI context that survives the chat window. Persistent repo memory, impact analysis, and instant style audits in one command.
Minimal prompt-driven workflow for giving coding agents a stable repository contract and a refreshable LLM-facing codebase wiki.
Open Vibe Architecture (OVA): architecture-as-markdown framework and Python CLI for coding-agent repositories.
AI Multi-Agent Documentation Writer using LangGraph, LangChain, and Google Gemini API
CodeMentorAI is an AI-powered codebase mentor that helps users analyze, understand, and interact with GitHub repositories using retrieval-augmented generation, repository summarization, architecture insights, bug detection, and conversational code Q&A built on Streamlit and Groq.
Ask questions about a codebase and get grounded, cited answers.
Spring Boot + MyBatis 框架感知代码地图:静态分析调用链/SQL/事务/实体影响面,通过 MCP 喂给 AI 编程工具(Trae/Cursor/Claude Code),省 token、防幻觉
Architecto est un agent IA « Software Architect » : il assiste la conception logicielle (analyse de besoins, choix d'architecture, ADR, diagrammes, revue de code) en s'appuyant sur une base de connaissances vectorielle.
Catch documentation drift by safely validating explicitly marked code examples in Markdown.
Grade and converge a repo's documentation as an AI-agent context source — six-dimension star rating (completeness, correctness, freshness, linkage, consistency, economy) including entry-file token cost, plus a loop that fixes the docs until targets are met. A Claude Code skill.
Semantic code map and code graph MCP server for AI coding agents, powered by SCIP and Tree-sitter.
AI-native Emacs successor — Rust core, R7RS Scheme, collaborative editing, LSP/DAP, Babel, 130+ AI tools, GUI + terminal
Agent-driven code intelligence engine: Python/FastAPI agent orchestration, Rust/Axum code graph and context compression, plus a React + Vite WebUI. Early-stage, work in progress.
Cursor Skill:开题或做计划前的全网类似技术调研(GitHub 开源为主),结果在对话里交付
An agentic AI skill that analyzes codebases to create, review, and incrementally maintain clear, structured project documentation
Syngraphe keeps repository context versioned, current, and understandable by both humans and coding agents.
Self-hosted semantic code search. Index repos and knowledge sources into a local vector DB, then search by natural language from CLI or any MCP-compatible agent.
codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work
Cross-platform file collection for LLMs — tree checkboxes, drag-and-drop sorting, encoding detection, one-click merged TXT · Flet port of Sam-Fic/FileCollector
Find your forgotten side projects and figure out what to ship next. Scans local + GitHub, diagnoses health with Claude, suggests next steps.
Deterministic Go code editing for LLM agents. AST-based CLI and MCP server that replaces Edit, Read, and Grep on .go files for Claude Code, Cursor, and any agent.
Leap over the browser. Real-time bidirectional sync between Overleaf and your local filesystem.
Make direct questions to multiple github repositories at the same time with AI.
Retrieval-Augmented Generation (RAG) system over a code repository for a question-answering task
Winning project for Hack Kosice 2024. Codebase resurrection platform, made as a web app in Typescript and Python, utilizing LLMs
⚙️ Dr. Document – a multi-agent 🚀 AI documentation generator using LongCat instances with iterative workflows, specialized agents for code analysis, requirements extraction, and management oversight, plus GitHub integration for automated README generation and validation cycles.
AI Coding Agent, Agentic Harness, Semantic Code Search Engine
ArcDoc+ Architecture Documentation Framework
Agent-first runtime tooling for Spring Boot: execution graphs, governed overlays, and reviewable remediation drafts for coding agents.
Forensic git-history learning diagnostic for AI-assisted developers. ICM specialist that turns commit history into evidence-backed study plans and HTML reports.
What is KONKMENG? KONKMENG is a bilingual (Khmer/English) AI-powered code analysis tool that helps Khmer developers understand, debug, and improve their code through instant, line-by-line explanations in their preferred language.
Coda Formula Language integration for Google Antigravity with AI-powered formula generation
VSCode extension that search file with Greptile RAG
LLM-based Listwise Reranker for Retrieval-Augmented Generation (RAG) over GitHub code repositories. Includes advanced retrieval, reranking, summarization, and evaluation with Recall@K.
A 100% local semantic code search tool featuring hybrid search (vector + BM25), AST-aware chunking, and native MCP integration for AI coding assistants.
📜 A universal documentation standard that gives AI agents instant project context via structured history, semantic vector search, and commit-triggered automation. By Oveja 🐑