Havuz

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversar

Let Claude Code, Codex and Pi talk to each other: cross-session messaging that wakes AI agents on one machine or across your LAN (macOS/Linu

Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and gov

High-assurance, artifact-agnostic prompt for authorized security labs, exploit-chain research, PoC validation, and evidence-led reporting.

Mako — AI Career Intelligence System

Open-source, local-first AI team workspace. Several AI models work together in one conversation, each with its own provider, model and tool

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-

Standalone MCP server for cross-pane AI agent communication via tmux. Lets Claude Code, Gemini CLI, Codex, and Kimi CLI talk to each other t

拾忆 ShiYi · 个人 AI 工作台（Android / Windows）：能读写文件、跑命令、联网搜索，带长期记忆 / 技能 / 子代理 / 多 Agent 群聊 / 内置 Alpine 终端，可切拾忆本地引擎或 DeepSeek Harness

基于pi-agent自己开发的一个agent desktop工具

Local-first desktop app for AI agent teams. Runs with Ollama or cloud models. Mac + Windows.

A spatial workspace for directing AI coding agents like an engineering director

Put everything on your wallpaper. Terse is a live 3D particle wallpaper for macOS & Windows: synced song lyrics, notifications, window title

Brigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP an

学习 learn-claude-code 后的 PR Review Agent 实践项目：构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

One prompt. A full AI engineering team. Go lie on the couch. 🧠

Vibe Mathematics —— 多代理数学问题求解与形式化验证框架

A Claude Code custom skill that turns Claude into a Tech Lead — coordinating parallel Worker Agents through a full dev workflow: PRD alignme

Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, g

Claude Code production-readiness audit plugin with 8 specialist lenses in 3 waves for security, reliability, tests, DevOps, live-app QA, and

🚀 AI 全链路求职自动化平台：抓取→清洗→AI评估→简历改写→自动投递，四大招聘平台 + 飞书 ChatOps 指挥 | Industrial-grade AI job-hunting automation: scrape → clean → LLM eval → resume

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewe

SDKs and reference implementations for the Synadia Agent Protocol for NATS

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

Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Code, OpenClaw, Cursor, Codex, G

The desktop AI agent for the real web. Built-in fingerprint browsers, saved logins, multi-agent orchestration, and reusable Browser Skills b

maw — CLI for running multiple AI agents across machines via tmux. Wake agents, talk across nodes, watch screens, track cost. Engine-agnosti

Local-first Electron cockpit for the Codex SDK, OpenRouter, multi-agent crews, and bounded computer access.

Two peer coding agents that work as equals: shared plans, live collaboration, isolated Git worktrees, cross-review and joint sign-off. Drive

A minimal Codex skill that delegates work to specialized agents and verifies the result.

Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests

One terminal for Claude Code, Codex, Gemini CLI and 30+ coding agents. Run them side by side or as a team.

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

Pi 一站式扩展：并行子代理、自动修复的多模型审查、清爽界面 · All-in-one Pi extension: parallel sub-agents, self-fixing multi-model review, a calm UI.

Web-based visual platform to orchestrate multi-agent Claude Code workflows. Create agents, chain them into pipelines, watch them collaborate

An open-source recreation of AI Co-Scientist: a multi-agent scientific research harness.

Hermes plugin: one /crew message becomes verified work on the kanban board. A coordinator owns every card until its proof passes.

Code for the paper "Emergent Collusion in Long-Horizon LLM Agent Interaction"

Your AI agents, always on, working together. Claude Code, Antigravity and Codex on your own computer.

Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run

Visual AI workflow orchestrator for DeepSeek Harness (dsh): multi-agent DAGs, live execution, recovery, and Feishu integration.

Workflow-as-code orchestration for Codex

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

Multi-agent macro trading bot: multi-factor stock scoring, momentum portfolio construction, backtesting vs SPY/Nasdaq, and live Alpaca execu

Hands-on workshop to build, test, and deploy single-agent and multi-agent Hosted Agents to Microsoft Foundry from VS Code using Foundry Tool

Send any file to any agent — yours or anyone's. One drive shared by every AI you use (ChatGPT, Claude, Muse, coding agents), an address per

A TUI agent orchestrator for power users.

ValuSee 是面向消费者的 AI 购物决策与省钱平台，支持商品截图与浏览器扩展采集、SKU 同款及规格识别、跨平台真实到手价核算、评论证据与购买风险分析，并结合预算、已有设备和偏好生成个性化建议；持续提供历史价格、降价监控、保价、退货、保修及买后管理。

Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.