Havuz

面向企业研发团队的多人、多 AI Coding Agent 协作控制平台。以人为责任主体，以 Agent 为执行代理，通过统一任务、上下文、事件与成果协议连接不同 AI 客户端。

A2A protocol wrappers that turn AI backends into interoperable agents. Drop a JSON config, get a spec-compliant A2A server. Supports GitHub

Plan, run, and track AI coding work feature by feature—with local Markdown cards, diagrams and Git worktrees.

The open infrastructure standard and reference implementation for AI agent cooperation, discovery, and marketplace.

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

Uxnan (pronounced /uʃ.nan/) is a suite of tools I built to solve a very specific problem I face as a developer: managing AI-powered coding a

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out

The last harness you'll ever need.

Multi-model delegation for Codex: native and ACP workers, main-session context separation, and a local Dispatch dashboard.

Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering,

Hand your software work to Claude Code, Codex and GitHub Copilot agents and steer it from a local board, in the browser or on your phone.

Fable 指揮官工作流 — 最強模型只做規劃/審查，研究與執行派給你選的模型；maker/verifier 分離的執行迴圈。Commander workflow for Claude Code: plan & review on the top model, delegate

Your coding agent says "done". Orvant asks for proof. A skill for Claude Code, Codex and other file-capable agents, plus a Python engine tha

Multi-agent orchestration system built on Elixir/OTP. DAG workflows + mesh mode + real-time LiveView dashboards on local, docker , and kube

Multi-Agent Continuity Layer — Keep your AI agents on a single, observable, handoff-ready work thread

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every

A new kind of IDE for agentic engineering

Telegram bot for Claude Code and Codex CLI with MCP routing, multi-agent orchestration, cron jobs, and access controls.

Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.

RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.

Agentic game development for building games with AI Agents. Run one session per seat: art, gameplay, narrative, QA, audio, tech all in 1 spo

Native OpenCoven workspace for familiars, agent sessions, memory, tools, workflows, and local-first development.

Caravel — a local-first workspace for AI coding agents. Delegate tasks, follow progress, and review code across projects.

Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step mod

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

Human-in-the-loop multi-agent task orchestration platform for Git-based software workflows.

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-

Self-hosted remote control for Claude Code, Codex, OpenCode, Kimi Code, Grok Build and Cursor: run coding agents on your own machines and su

Open-source multi-agent coding harness. Coordinate Claude Code, Codex, Cursor, Gemini CLI, Copilot, and more to split work, communicate, and

Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.

The open-source workspace for coding agents. supermux runs Claude Code, Codex, and other coding agents on your own computer or server, many

Evidence-gated Claude and Codex council orchestration.

Run and control every coding agent from one desktop app: Claude Code, Codex, OpenCode and more, across your Mac and servers, with GOD of Age

Diverter distills Ultra’s delegation strategy into non-Ultra Codex sessions—bringing in the right native specialist while the main thread ke

Every coding agent, every account, one app: run Codex, Claude Code and other agent CLIs with the sign-in you already have.

Autonomous software engineer. Researches, plans, builds, commits, fixes bugs, loops until done.

Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.

A native macOS multi-agent terminal orchestrator: manager-driven agent trees for Claude Code, Codex, and OpenCode

Open platform for running Managed Agents at scale

Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the da

Run many Codex & Claude agents in parallel without them overwriting each other. Isolated worktrees, file locks, PR-only merges. Auto-wires O

Your coding agent gaslights you. GODKILLER doesn't. Disk gates > vibes. claim_done only after verify.

The agent that evolves with you 𖤍

Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion.

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

Turn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Co

Mission control for parallel Claude Code & Codex sessions — a live grid of coding agents that glow when they need you, across multiple accou

Turn Claude Code into a voice-enabled, multi-channel assistant that runs tasks in parallel

Local-first AI project OS that turns coding models into reliable software agents with memory, sandboxed execution, verification, recovery, G