Havuz

🔌 An Android Studio plugin exposing native Gemini tools as an MCP server. Enable external AI assistants (Claude, Copilot) to call Android-sp

Slash commands and MCP servers for AI agents, written once and compiled everywhere.

Hand a live Claude Code, Codex, or opencode session to anyone with three spoken words - encrypted, no account. Or carry your whole Claude Co

A platform evolution of OpenAI Symphony (openai/symphony) for running Codex, Claude Code, CodeBuddy Code, and OpenCode from real project tas

Open-source terminal AI coding agent with persistent local memory, automatic context recall, and searchable cross-session history.

tideSI (tidesi) – AI usage & quota widget – Yeah, I know yet another SI/AI usage widget, but I wanted one for my own NixOS setup that just

Rust drop-in for the opencode server. Speaks the v1 API (1.18.x) and the opencode 2 /api surface: all 142 v2 ops bound, 2.x clients need OCS

Netbeans Plugin to integrate with Coding Harnesses like Claude, Cursor, OpenCode, Pi, Hermes and Goose using ACP

Plugins for OpenCode v2: model prices and credit, live GO usage, plugin auto-update, phone alerts, git state, session search, and a cup of c

Self-hosted LLM gateway in Rust: one OpenAI- and Anthropic-compatible endpoint for Claude, Codex, Qoder, Cline, Grok, Antigravity, CodeBuddy

Claude.ai in your terminal: streaming chat, OpenAI proxy, MCP server. No API key.

Volcengine skills and plugins for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI, OpenCode): manage cloud resources via the `ve` C

Turn an agreed plan into milestones, stages and gates, built by delegated coding agents and reviewed by you. Works in Claude Code and any ot

Your AI coding agents keep working while you sleep. Drive Claude Code, Codex, Gemini, opencode & more from your phone: resume past usage lim

Agent skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of "97 Things Every Programmer Should Know"

A complete engineering team in one folder: 26 specialist agents, 20 workflow skills, orchestrated workflows and quality gates.

A living local memory layer for your coding agents and AI tools.

把实现计划派发给另一个 AI 执行，你只负责审——纯 CLI 的协调者/executor 两角色协作工具（opencode / Claude Code / grok / codex，支持远程开发机）

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review,

Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode

Turn any supported coding-agent harness into a full game-dev studio - 55 specialized AI agents and 182 skills for Godot, Unity, Unreal, Thre

OpenCode GitHub agent in GitHub Actions

An AI desktop app that runs on your own keys. Chat with any model, let always-on Workers take jobs off your plate, and run every coding agen

Quiet tmux status for Claude Code, Codex, opencode & pi — shows nothing while agents work, a small marker when one needs you. No dashboard,

zen-proxy is a local translation proxy that bridges Claude Code's Anthropic Messages API with OpenCode Zen's OpenAI‑compatible Chat Completi

Use [Multi]ple AI agents for code-review, verifying and questions

AI-powered PRD Generator Skill Generate Product Requirements Documents through warm conversational interviews. Works with Claude Code, Codex

Skills tell your AI coding agent what to do. Bossku checks that it did. It makes the agent test its code, stops risky commands and remembers

ACP-friendly Node.js SDK for local coding agents: run Codex, Claude Code, Cursor, OpenCode, and Pi with streaming, abort, and session resume

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become perman

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

Your agent sleeps. The event wakes it. Durable timers and event triggers that wake OpenCode sessions.

Universal OpenCode TUI sidebar for browsing provider agents and subagents

Understand code by watching it run in slow motion. An agent skill that builds interactive, plain-language explainers: system maps, step-by-s

Create autonomous teams of agents. Define roles and communication, mix Claude Code, Codex, OpenCode and Gemini CLI, and run them in the back

A terminal for AI coding agents on Linux and macOS, with workspaces, notifications, and a browser agents can control.

Visual session-state signals for OpenCode using its native theme system

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

All your work and agents in one place

Git and GitHub side panel for OpenCode Desktop: graph, PRs, reviews, CI, issues, triage, and agent tools with an approval queue

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and l

Personality layer for coding agents. Same code, different voice: yo / dawg / mafa / off.

Browser automation for Chromium-based browsers (Chrome, Edge, Brave) via OpenCode - readable extension, native messaging host, and OpenCode

A canvas for your coding agent. It draws what it means, asks you with pictures, and walks you through its changes and reviews, right beside

Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everythi

Autonomous development loops for Claude Code, Codex and OpenCode. Adds planning, implementation, checks and cycle state to new or existing p

Terminal discovery hub and package manager for AI coding tools, MCP servers, and agent skills. Built with Python & Textual

帮助每一个人快速上手vibe coding和agent的学习，体会vibe的乐趣。教程包含常见概念扫盲、dify、opencode、codex、trae的使用指南；还会手搓一个mini agent深入理解底层原理；最后还包含langchain和langraph框架的入门和学习教程