Havuz

Instant messaging between coding agent sessions — Claude Code, Codex, opencode, Cursor CLI, MiniMax Code and ZCode — across tools, to other

Group chat for humans and coding agents. Mention @claude, @codex, @cursor or @gemini in a channel: the agent runs on your machine with your

Multi-Agent AI 工作台 (AgentCore) — 真正的 Agent 团队协作，而非单 Agent 子任务派发

Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, pic

A visual multi-agent desktop for Codex: live tasks, shared projects, isolated Missions, and OpenCodex models on Windows.

数模Agent（数模 Agent）/ 数学建模 AI 助手：多智能体协作完成题意分析、文献检索、建模、代码执行与论文写作，支持人工审核和断点恢复。Local-first multi-agent workbench for mathematical modeling.

Run-aware token governance for multi-agent systems.

Nirvana-OS engine: ready-to-run agentic operations. One sentence in, finished work out. Source-available engine for companies, squads and mi

基于 LangGraph 的多 Agent 深度研究助手：可中断恢复、按依赖并行、引用治理与评测，成本降低 45%

A Codex skill for CTO, product manager, and engineer teams with task routing and completion follow-up.

Give your agents a soul. Soulgent turns every Claude Code, Codex and WorkBuddy session on your Mac into a character you can see: who is work

A template for building apps with a small fleet of Hermes Agent profiles: one coordinator, six specialists, two human approval gates.

Give it a goal. Watch an organization grow. A visual multi-agent system: one sentence grows into a team of AI agents that plan, split the wo

T3MP3ST, mevcut AI coding agent'ları veya yerel modelleri kullanarak yetkili güvenlik testlerini recon, exploit ve raporlama adımlarında koordine eden bir red-teaming platformudur.

Neden yükseliyor · 87 günlük yaşına karşılık 6256 yıldız ve son 28 günde 30 commit ile dikkat çekiyor; README'deki XBOW benchmark sonucu ve mevcut agent'larla ek API anahtarı gerektirmeden çalışma iddiası da ilgiyi artırmış olabilir. Son 28 gündeki 4 farklı yazar proje aktivitesine işaret ediyor; ancak yıldızlar tek başına kullanım veya kalite kanıtı değil.

AutoCVE, kaynak kodu üzerinde agent tabanlı güvenlik denetimi yapıp bulguları doğrulamayı ve CVE başvuru raporları üretmeyi amaçlayan bir platformdur.

Neden yükseliyor · 104 günde 1416 yıldıza ulaşmış olması ve README’de 14 projede bir haftada 30 güvenlik açığı bulup başvuruya sunduğu iddiası dikkat çekiyor. Ancak yıldızlar ve README’deki sonuç beyanı tek başına etkinliğin kalitesini veya tekrarlanabilirliğini kanıtlamaz; son 28 gündeki 4 commit ve 2 farklı yazar aktivitenin sınırlı olduğuna işaret ediyor.

DeterminFlow, Agent, script ve API adımlarını doğrulama, checkpoint, retry ve recovery özellikleriyle çalıştıran Python tabanlı bir AI workflow runtime sunuyor.

Neden yükseliyor · 56 günlük bir repoda 763 yıldız ve son 28 günde 28 commit dikkat çekiyor. README, gerçek bir AI yazım iş akışında kullanıldığını ve Token tasarrufu sağladığını bildiriyor; ancak bu örnek ve tasarruf tahminleri bağımsız doğrulanmış kanıt olarak değerlendirilmemeli. Son 28 gündeki commit’lerin tek yazardan gelmesi aktivitenin sürdürülebilirliğine dair belirsizlik bırakıyor.

PeerBridge MCP, farklı coding agent'ları yerel bir çalışma alanında yönetip görev, izin ve kanıt kayıtlarını ortak bir kontrol odasında birleştirir.

Neden yükseliyor · 41 günde 239 yıldıza ulaşmış; ancak bunun nedenini gösteren veri yok. README'deki çoklu agent yönetimi ve audit/evidence yaklaşımı ilgi çekici olsa da son 28 günde 4 commit ve 1 farklı yazar, sürdürülen geliştirme ve bağımsız katkı hakkında sınırlı kanıt sunuyor.

Open-source local workbench for multi-agent software development.

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

China's 1st enterprise multi-agent IT ops platform. LLM-powered auto-remediation for Zabbix/Prometheus. Docker deploy.

A code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows

DataBuff is an AI-native APM built on Opentelemetry，with multi-agent troubleshooting out of the box.

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new archi

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multipl

Solo Agent — an open-source, local-first workspace where humans and AI coding agents collaborate through channels, tasks, teams, and persist

The open source operating system for AI-powered businesses

Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

An agent-first task board, Take human out of the loop.

AutoHarness: Automated Harness Engineering for AI Agents

Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, G

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Web UI & dashboard for Hermes Agent — chat, memory, skills, terminal, approvals, multi-agent orchestration. Self-hosted.

结合多大模型分析与确定性代码风控的自主量化交易系统 ｜ Autonomous crypto trading system with multi-LLM analysis, deterministic Python risk control & OKX execution.

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orches

Transform any idea into a running AI-powered company

Turn Codex threads into an organization of long-lived domain agents.

Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound.

Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer

An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 1

A safe bridge for Codex and ChatGPT to hand off coding work, save tokens, and keep local execution under control.

Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).

Put your idea on trial in front of a jury of 12 Claudes. A free Claude Code skill.

🧬 Symbio（共生）- AI Infra 级多 Agent 协同框架 | 33 Killer Features: 动态 DAG, 本体化记忆, 防过早完成, 数据飞轮, 神经符号安全, OpenTelemetry 可观测, HITL 人类介入, MCP 原生支持, 语义缓存,