Havuz

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

聚合精选编程 AI 扩展资源：MCP Servers、Skills、Rules、Prompts，周更索引 + 一键安装。

A native Rust CLI for orchestrating AI agents across projects, with persistent sessions, worktrees, and local-first control.

Free, open-source API testing desktop app built with Rust. No account, no cloud, no telemetry.

Compartment is a self-hosted deployment system for small software on infrastructure your team controls.

Git-native memory for coding agents. Repo memory before the diff.

Reusable AI coding workflows for Claude Code and VS Code to ship auth, billing, and landing pages faster.

Project Management for the agent era

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, c

An open-source build system that compiles your specs and architecture into working code.

A native macOS GUI for Jujutsu (jj) — DAG graph, side-by-side diffs, interdiff, conflict resolution. Built with Rust + SwiftUI.

Carbon Code 是一款类似 Claude Code 的代码开发工具，也是中国第一个基于 DeepSeek 的代码开发工具，Token 成本节省 90% 以上。它可以实现自动任务拆分、自动开发、MCP 测试，以及与 Claude、Codex 等多 Agent 协作，能力接近

Agentic Engineering that actually scales. Run Claude Code, Codex, Gemini and any other CLI Agents in parallel with upto 86% fewer tokens and

Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.

Control your local Codex sessions remotely through Discord on your phone or browser.

The Git client that actually resolves conflicts: 8 deterministic patterns auto-resolve the ones that were never decisions, full trace on the

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens

Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS/Swift). Security

Sync your local skills across 41+ AI coding agents with a single command.

A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work

An open-source, terminal-based AI coding agent that reads your code, calls tools, and helps you build.

OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles th

Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions.

Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history,

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server

One file. Under 200 lines. Zero dependencies. It's a coding agent.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, and deploy across all major AI

Run multiple AI coding accounts at the same time.

Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude Code, and opencode.

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in pa

Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.

A Mac vault that runs authenticated actions for AI agents over MCP. The agent gets the operation, never the key: no command reveals a stored

macOS desktop widget for Claude Code. See what Claude is doing, respond by voice, never miss a permission request.

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

Cover your Mac's screen with a hotkey while AI agents keep running, even with the lid closed. The covered screen glows when Claude Code, Cod

A Claude Code skill that burns tokens on demand. Stress test, inflate metrics, or just set money on fire.

The ADE (agentic development environment) for running a team of coding agents: start a job with a chat, answer what needs you with the evide

MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.

Model-neutral AI workspace for macOS with multi-provider models, extensible tools, and inspectable deliverables.

Open-source universal AWS resource browser for MiniStack, Floci, LocalStack, Moto, and real AWS

Self-hosted notification infrastructure for product notifications. One notify() call handles email, SMS, push, etc, with preferences, quiet

A persistent incremental diff review loop for pi

Boring Is All You Need: a Codex Desktop workflow replacement with transactional migration, audit-only managed hooks, risk-based review, scop

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.

Stop hooks that stop AI coding agents (Claude Code, Codex) from claiming "done" without proof. A Lean quality system: every defect becomes a

A macOS Dynamic Island for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, hooks, skills, and local agent management.