Coding agents & developer tools
Codebase search & documentation
1,704 agents · most starred first
Codebase search & documentation, page 10 of 18
This project leverages the power of OpenAI's GPT-4 Turbo with vision to process UML sequence diagram images. The tool then generates code snippets in your preferred programming language, framework, and software architecture. Plus, it's now in an exciting beta phase, so you get to be a part of the journey!
Ruby OpenAI client with support for generating code from prompts & running the generated code
Application for cloning and exploring Git repos and local directories. Browse repos, visualize directories, preview code, generate AI explanations, and analyze file sizes.
VS Code extension to generate C# XML documentation using Open AI API.
🔍 Enhance code searches with ast-grep, finding patterns in your code structure for improved error handling and analysis.
CodeMap is a CLI tool that generates optimized markdown docs and streamline Git workflows.
Leaked Claude Code (Claude CLI) full architecture — 1,902 files, 512K lines, 89 feature gates, 39 tools, 101 commands. Analyzed by Claude itself. All numbers verified.
Code Documentation, redefined: Where AI Meets Clarity!
AI-powered codebase onboarding tool — point it at any repo and ask questions about the code. Uses tree-sitter parsing, RAG, and local LLMs.
AI-driven code analysis & automated README generator using GraphRAG and AST parsing.
WTF? What's This Function? 这是什 码?— Double-tap Ctrl → instantly explain any code. Desktop AI code reader powered by DeepSeek/OpenAI — select code anywhere → Ctrl+C → double-tap Ctrl → Chinese explanation with signature, runnable examples, gotchas. Like Youdao Dictionary, but for code. 选中Ctrl C + 双击 Ctrl 即刻解读代码中的函数,极度适合代码学习者。
Modern QnA platform for developers.
Local-first context engine for coding agents: project skeleton, symbols, references, graph, retrieval, confidence, MCP, CLI, and HTTP API.
AI-CLI 时代的 data lens:把 Claude Code 的 jsonl 实时镜像成可读 HTML,带跨 session 搜索 / 知识图谱 / 自动周报。零 token,单文件 Python。
Local-first MCP server that tells coding agents which files to read, and how sure it is. 97% Hit@10 on Java (SWE-bench Multilingual), 89% on Python (SWE-bench Lite), zero LLM cost. mcp-brain calibrate re-measures it on your own Git history. Plus team memory and conflict checks.
Reverse-engineered source code architecture of Claude Code CLI — 4,756 TypeScript files reconstructed from cli.js.map. Deep analysis of QueryEngine, Tools, Bridge, MCP integration, Ink UI, and more.
Agent/Human CMS grounding and management
An agentic code context engine MCP+CLI which pre-compiles an llm-described AST in the .tost format, greatly reducing context bloat and token costs for agentic coding tasks
Responsible use of generative AI in assisted coding
Convert any code repository into a single markdown file for NotebookLM and other LLM tools.
Cross-repo agent index layer. Stop dumping 400k tokens — index your repos once, query like a database.
Generate source-of-truth docs from a codebase, API specs, or document folders. Get an indexed, version-pinned pack, hashed to its source. Then code or discuss with your Codex/Claude Code agent.
Align product intent, code reality, and agent context for engineering teams.
Open-source, language-agnostic documentation tooling that bridges code and docs. Built for humans, LLM agents, and dev workflows.
Tool to export any project folder or repository into a single, neatly formatted file — ideal for quick AI-assisted code review, debugging and refactoring. Collects source files recursively, wraps them in fenced code blocks with relative paths, filters noise (e.g. node_modules, .git), shows basic stats and supports optional clipboard copying.
Pack your codebase into a single file for AI analysis
AI-powered repo narrator — paste a GitHub URL and get overviews, file summaries, Mermaid diagrams, and RAG-backed chat. Built with Next.js & Gemini.
A production-ready knowledge graph system for software engineering that connects design patterns, refactoring techniques, and software laws through semantic relationships. Built for AI agents first — integrate software engineering expertise directly into Claude Code, Cursor, and other MCP-compatible tools.
Interactive graph theory platform for simulating and visualizing the Hierholzer algorithm in real-time. Inspired by the Seven Bridges of Königsberg puzzle. Developed for two platforms: web and desktop.
Turn any repo into a Code Knowledge Graph your coding agent can reason over — symbols, API routes, ORM models, architecture decisions & git history as a typed, provenance-tracked graph, served over MCP. Built on AgentForge.
Local graph memory for AI coding agents, giving MCP-compatible tools precise codebase context before they edit.
docker streamlit region:us
Durable, repository-owned project knowledge and lightweight delivery for AI coding agents.
Reusable AI agent skills for architecture documentation, ADRs and diagramming
Structural code intelligence for humans and AI agents
Local code intelligence graph for AI coding agents: Tree-sitter static analysis, structural code search, dependency impact, blast-radius analysis, CLI and MCP server.
AI-powered code assistant that helps support and engineering teams understand and navigate code repositories.
AI-Powered Documentation Generator for Claude Code
Keep long-running repository work coherent and easy to resume.
Graph-powered code intelligence for AI agents — a Rust engine that maps your whole codebase into a knowledge graph and serves it over MCP, so Claude/Codex/Cursor answer structural questions with ~40x less context.
Fast local code intelligence for AI agents powered by AST Treesitter, SCIP, semantic search and a reranker
Agentic tool that reverse-engineers COBOL applications into structured requirements, business rules, and dependency graphs using the Claude Agent SDK
One question about your own code, when you finish coding. A SessionEnd hook for Claude Code that asks you about the mechanism you just shipped.
A Claude Code skill that keeps a plain-language map of your codebase, for people who build software through AI and cannot read the code themselves.
WIP: Design the LSP(language server) but for Agent. native parser and ast understanding first.
Source-free architecture maps and deterministic polyglot refactoring for AI coding agents
Living architecture control plane for the AI-dev era. Derive real architecture from code, keep living docs + ADRs, enforce intent in CI, and steer AI agents to conform. Local-first, MIT.
📖 Auto-generate feature-based documentation structure (AGENTS.md + docs/) for any project.
Search through your Claude Code history
llmwiki (Quiz_wiki) — auto-captures your coding-agent sessions (Claude Code / Codex / OpenCode) into a compounding, local-first project wiki that quizzes you back. The llmwiki quiz is a daily forgetting-curve quiz (/wiki-quiz) that keeps your memory of your own decisions sharp. Markdown as source of truth, no MCP, no build.
AI-driven architecture browser: MCP server + desktop app. Claude Code, Codex & other AI agents explain your codebase with guided walkthroughs, diagrams and visual artifacts. Read-only, local-first. Tauri + Rust + Svelte.
AgentReady — Transform any legacy repo into an AI-agent-ready codebase. Generates agent-context.json, AGENTS.md, CLAUDE.md, MCP config, and tool scaffolds via a single GitHub issue or Actions workflow.
Your AI agent reads the codebase. You speedread the report. An agent skill + one-file RSVP reader for markdown reports.
LLM Knowledge Management • Wiki-grounded verification • RFC-based documentation • Best practices automation • AI-native engineering
Token-efficient code knowledge graph for AI coding agents — type-checker-accurate call graphs for Go & TypeScript/JS, served over MCP.
Hermes Agent plugin — private local code memory for your repos (semantic search, file reads, grounded Q&A)
A plug-and-play framework for AI-assisted software development, enhancing context-aware collaboration in complex codebases. Perfect for tools like GitHub Copilot. 🐙✨
PolyForge: a Rust CLI toolkit that turns any GitHub repo into an agent-verifiable knowledge base via MCP (Model Context Protocol) with a Merkle hash evidence ledger.
Open standard for AI-readable software specifications — Markdown+YAML features, requirements, acceptance criteria, plans and tasks, validated by CI lint
Pack a repo into one AI-friendly file — or keep only the lines that matter for one task, with a verification receipt.
Analyze any repo and generate reconstruction PRDs to rebuild it from scratch
Show an AI coding assistant only the code that matters for the change it's making. Measures whether it actually works on your repo.
Evidence and verification for AI coding agents: map code, reuse concepts, finish migrations, and gate diffs.
Bimbus AI: a Node.js command line tool utilizing OpenAI's GPT language model APIs for automated code documentation generation, boosting code comprehension, collaboration, and development efficiency. Streamline your workflow and unleash the full potential of your code with Bimbus 🚀✨
Intelligent codebase context engine for AI coding agents. Semantic RAG from source code via MCP tools.
Deterministic blast radius for every change. Verified impact on every PR, self-updating architecture docs, autonomy earned via eval scores.
codex docs
Find, search, and resume every AI coding session on your machine — and trace any file back to the conversation that wrote it. Across 11 AI coding tools (Claude Code, Codex, Gemini CLI, OpenCode, Cline, and more). 100% local, no telemetry.
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.
See which notes your coding agent actually reads — a live radar for Claude Code and your Obsidian vault.
Local-first semantic search across tens of thousands of agent skills (SKILL.md) for Claude Code, Codex & OpenClaw — describe your task, get ranked matches with install commands. FAISS + Ollama, no API calls.
Analyze any repository into agent-ready onboarding context: commands, entrypoints, security audit, quickstarts, and SKILL.md.
Generate source-of-truth docs from a codebase, API specs, or document folders. Get an indexed, version-pinned pack, hashed to its source. Then code or discuss with your Codex/Claude Code agent.
AI-powered codebase Q&A to explore repositories, docs, and project insights
Fully local MCP retrieval tool for coding agents. 161M encoder, ~1s per tool call, no API, no LLM in the query path. No file reads: line numbers, callers, callees and exact call sites, packed to a token budget. 2-4x the file coverage of BM25 and TF-IDF on SWE-Explore, and tops the paper's own sub-1B code model on CORE-Bench.
MCP context engine for AI coding agents: a local code graph answers "which files does this task need?" — folded evidence packets instead of whole files. Recall 1.000 on repos it was never tuned on, 45% fewer context tokens in a real Claude Code session. Rust, local-first, MIT.
Local-first code navigation index and feature-to-evidence chain for AI coding agents: tree-sitter symbol index, project memory, YAML feature specs, an operations journal and PROVEN/FAILED proof from test runs. Rust CLI.
Fast semantic code search powered by Jev. Find the relevant files, line ranges, and snippets
Evaluation harness for code-retrieval agents: mines ground truth from git commit history, then scores any agent on weighted F1 and end-to-end latency.
Verified context for coding agents. Stop rediscovering your codebase.
Research, Evolve, and Document for AI-assisted engineering
A queryable code symbol graph for multi-language monorepos — find callers, impact, dead code, and cross-file inconsistencies, every edge confidence-scored.
The Modern System Design Workbench: 60+ interactive patterns, real-time capacity calculator, AI/LLM architectures, and interview-ready templates.
Evidence-backed code context for AI coding agents: semantic + lexical search, a cross-project code and contract graph, and versioned team memory across all your repositories — served over MCP, CLI and a local panel.
Reconcile every AI coding agent's conversation history (Claude Code, Codex, Gemini, Cursor, Aider, opencode, Cline +11 more) with git & docs into one cited ground truth — and generate ADR/PDR/BDR decision records. Local, deterministic, zero-deps agent skill.
Agent Skill that writes or refreshes a repository README from verified code, manifests, scripts and tests — no invented commands, badges or claims. Works in Claude Code, Codex and Cursor.
The deterministic harness a coding agent should be standing on: code shape, call graph, diff impact and crash state in milliseconds, offline, with no model in the loop. One CLI, 17 languages, zero runtime dependencies.
Neper: a self-hosting systems language and compiler for x86-64 Linux and Windows — freestanding executables, generics and protocols, compile-time evaluation, and a byte-reproducible self-host.
A Python utility script that generates a directory structure overview and file contents while automatically
Stop re-reading your codebase: DSP CodeGen is a graph-based IR that gives coding agents persistent structural memory and deterministic polyglot codegen with typed contracts at language seams — impact analysis, incremental regeneration, verifiable gates. One-command install into 5 agent harnesses.
A memory of the codebase your AI agent can't get from grep: a persistent call graph, semantic search, and per-symbol review learnings over any repo. Self-hosted MCP server — Go, tree-sitter, Apache AGE.
Repository diagrams that cite their sources. Every edge names the file, line and commit it came from — and every file it could not read is listed by name. Six languages, zero dependencies, one self-contained HTML file. An agent skill for Claude Code, Cursor and Gemini CLI.
Native Mac app that turns your Claude Code and Codex history into something you can read, search and see. Everything stays on your Mac.
Realistic OpenSpec example repos — two fictional products with a full year of spec-driven git history (proposals, specs, ADRs, tasks, playbooks).
Semantica makes AI code provenance, attribution, and semantic lineage visible across commits, pull requests, and repositories.
Archify GitHub Just Got Insane — AI Visualizes Your Entire Codebase! Instant AI-powered codebase architecture diagram and system flow visualizer using Python and Ollama.
AI 驱动的架构治理桌面客户端:让 LLM agent 成为团队的架构地图工程师——自动归纳仓库架构地图(分层+健康度)、漂移检测、一键巡检、可审计的任务流水线(需求分析→方案设计→实施→审查→归档)。AI-driven architecture governance desktop client: LLM agents auto-induce repo architecture maps with health scores, drift detection, patrols and an auditable task pipeline.
Is Agent Code Less Maintainable Than Human Code?
Git-native why next to the code, with a pin check that proves it still matches. Agents retrieve stored why before they edit; hook and CI attest the attachment. Experimental 0.0.2.