Havuz

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

Anthropic API reverse proxy with prompt-cache injection and request body transforms

Safe Codex CLI setup installer with skills, AGENTS.md, profiles, and MCP defaults

Architecture-aware code search, dependency graphs, and impact analysis for Python, TypeScript, Rust, C#, Java, Go, Ruby, Rails, Free Pascal,

A multi-agent Dynamic Island for AI coding on macOS, with a lighter Windows edition. Track Codex, Claude Code, DSH and Kimi Code on both; ma

Generate Google Stitch compatible DESIGN.md files from any website using AI vision. Bring your own Gemini, OpenAI, Claude, or Ollama key. No

跨 agent 的 skill 管理器 + skill 推广工具，欢迎fork和pr。管理你所有 skill ，创建技能自带讲解pdf或ppt。支持各种Agent。

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, o

Multi-agent Claude Code skill for building apps and stuff

A native macOS menu bar app that shows your Claude.ai usage at a glance — colour-coded icon, live counter, reset timer. No API key needed.

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability

adOmnia is the open-source, Go-powered IDE built for the AI era. Let agents write the code. You take control: run, test, debug, and ship, al

Free AI code reviews on every pull request. Bring your own key (OpenRouter free tier works), runs in your repo as a GitHub Action - no quota

Optimize AI workflows with Arachne. Automatically assembles the perfect code context (Tree, Target, Deps, Semantic) to fit context windows w

Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite st

Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plug

CodexMeter：本地运行的 Codex 用量监控桌面工具，支持 5 小时 / 7 天额度、重置时间、小组件和本地安全存储。

Personal malleable interface. Everything is plugin. Ultrafast built on rust. Built for AI agents.

Turn private work into an NDA-safe credential that shows what you can build — and companies can trust more than a CV.

The remote-native terminal: your shell, the machine it runs on, and its files in one window. Durable SSH sessions, remote files, GPU and por

Claude Code and Codex working as one team: one shared memory (voice included), each sees the other's latest messages. Plus searchable notes,

A local-first developer desktop workspace for databases, Git, SSH, object storage, and clipboard history.

Turn scattered, duplicated AI-agent Skills into per-Agent Rosters—with evidence, receipts, and exact undo.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Archive pasted Codex chat images locally before temporary clipboard files disappear.

Minimize AI and Agent failures into minimal reproducible traces.

Write your repo rules in Markdown. AI enforces them — triages issues, reviews PRs, fixes bugs, merges code, cuts releases.

One-command installer for all AI Marketing Hub tools: Claude SEO, Claude Blog, Skill Forge, WP MCP Ultimate

A one-click installer that scaffolds a complete GitHub Copilot agentic coding environment into any project

Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

Context retrieval engine for AI agents — semantic + lexical search over codebases

A blank, working source of truth for Claude Code and Codex across macOS and Linux.

Your coding agents get an agreed plan, a check after each round of changes and a handover to the next session. Workflow plugin for Claude Co

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

Fast Python App Launcher Template 2026: Rapid Feature Deployment Kit for Developers

DeepSeek Harness plugin: deterministic data profiling, cleaning, and verification (dsh-data-quality)

Guarded, recoverable web ChatGPT automation for local Codex projects on Windows and macOS

Open-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ

File leasing for AI agent teams. One MCP server. Any IDE. Zero merge conflicts.

A free pit crew for your expensive coding agent: the superpowers development workflow, run by cheap workers.

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compile

Local-first desktop control center for OpenAI Codex — sessions, models, tokens, accounts, providers, and AGENTS.md.

Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API

Turn Claude Code into an autonomous software development team — 16 specialized agents, documentation-first pipeline, TDD slices in parallel

pick any past Claude Code session via fzf, then resume it from the right cwd

Architectural linting for Swift developers and coding agents

An extremely fast GitHub for pull request review: PRs open in 20 ms. Keyboard-first, macOS and Linux, CLI for coding agents.

Local Claude Code and Codex plugin that bounds oversized and repeated tool output, preserving complete redacted artifacts. Runs locally, mak