Havuz

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

Run Claude Code, Codex and Gemini side by side — and let them hand work to each other. Portable Windows terminal for AI CLIs.

Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority,

Your durable workspace across AI agents.

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)

Codex 三層多代理協作 Skill：Sol 統籌與複雜推理、Terra High／XHigh 處理視覺與操作、Luna Max 執行可重複工作。

Local patch + guide: make OpenAI Codex MultiAgentV2 subagent tasks work with DeepSeek and other non-OpenAI Responses providers (encrypted ag

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.

Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini.

Vibe Mathematics —— 多代理数学问题求解与形式化验证框架

Pair GPT‑5.6 Sol High orchestration with GPT‑5.6 Luna Max workers for bounded Codex tasks—with safe custom-agent setup, explicit guardrails,

Codex Skill for choosing and coordinating the smallest safe Agent setup.

The open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery f

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

多模型协作与智能辩论平台 — Multi-Agent 并行工作流 + RAG + 知识图谱，让多个 AI 像专家团队一样辩论、推理、共创

Multi-agent task orchestration for coding agents. Turn one goal into an ordered plan of tasks (each with its own runner, model and mode), th

aiduMEI⚕爱嘟优忆思——aidu Memory Engine Insight · 智能体通用智慧引擎——Excellent memory system for all agents.

MAC, doğal dildeki tasarım brief’lerinden düzenlenebilir CAD parçaları ve deneysel olarak çok parçalı assembly’ler üretir.

Neden yükseliyor · 59 günde 1006 yıldıza ulaşması, doğal dilden CAD üretimine yönelik ilgiyi ve görsel olarak etkileyici parça/assembly demolarını yansıtıyor. Ancak README, assembly örneklerinin seçilmiş çıktılar olduğunu ve ölçülmüş prompt başarı oranı sunmadığını belirtiyor; 28 günde 22 commit olsa da farklı yazar sayısının 1 olması benimseme ve sürdürülebilirlik kanıtını sınırlıyor.

NOVA AgentOS — 本地优先、证据优先、用户可控的桌面 AI Agent。把目标转化为真实文件、测试与可追溯交付。

A World of Tanks-style armored combat simulator built directly with Three.js and Vite: 220 vehicles, 33 destructible battlefields, and 13 mo

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Codex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees

Claude Code skill that delegates implementation to GPT-6.1 (whatever is the latest) Sol via Codex CLI, Claude plans and reviews the diff, So

Native AI workspace for macOS. Local and hosted models, agents, browser, terminal, voice, and mobile access. Locus is wallet-free; LocusX ad

Final Price AI Agent combining evidence-grounded discount rules, Elasticsearch hybrid retrieval, and Decimal calculations with auditable ste

Simplified Technical English for Code - extract, adapt, and enforce ASD-STE100 rules for software documentation. 9-agent pipeline, 59-test b

Poirot is a deep research agent kernel built for those who care about how agents are architected.

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

Experimental autonomous-agent living-room kernel with auditable boundaries.

Praxis and Hélène: self-hosted agents and a portable desktop with persistent memory, Forge teams, inspectable tools, preserved-source update

Local-first AI decision workspace with four competing perspectives, human approval, evidence tracking, and native macOS and Windows apps.

A plan-driven, multi-agent coding loop: separate planner, coder, and reviewer roles, each on the provider and model you choose, work togethe

Installable graph engineering for Claude Code, Codex, OpenCode, Cursor, and OpenClaw — dependency-graph execution with local caching, qualit

Graph Engineering, simplified — with GraphCode. #graphcode

A Rust-native, multi-agent development cockpit for macOS — spawn isolated worktrees, run CLI coding agents in parallel, and review every cha

Distributed AI multi-agent autonomous system — digital employees for long-horizon tasks, running 24×7 — Meta-bootstrapping · Real-autonomous

A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an

Interface web pour Hermes Agent, l'agent auto-apprenant de Nous Research : plusieurs agents avec rangs et pôles, délégation tracée, mémoire

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS inste

从 Java 开发者到 AI Agent 工程师的 30 天实战之路 | Spring Boot + Spring AI + MCP + Multi-Agent

AgentConnect, ekiplerin farklı mesajlaşma ve geliştirme platformları üzerinden birden fazla AI agent ile birlikte çalışmasını sağlayan açık kaynak bir platformdur.

Neden yükseliyor · 66 günde 1.436 yıldız ve son 28 günde 803 commit kayda değer ilgi ve geliştirme temposuna işaret ediyor; ancak aynı dönemde yalnızca 3 farklı yazar bulunması aktivitenin dar bir katkıcı grubunda yoğunlaştığını gösteriyor.

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

An experimental playground for open-source, all-in-one office AI for universities: code, docs, spreadsheets, slides, browser – all are the A

Auditable multi-agent A-share factor research, knowledge base, long-only backtesting, AutoCombine and QuantCombine.

多智能体小说写作框架 | Multi-agent novel-writing framework — 每个角色都有自己的脑子,每一章都有质量门禁

Decision infrastructure for agents. Verifiable, traceable, auditable.

Opt-in dual-agent workflow: Claude Code plans and reviews, Codex implements, deterministic gates verify, and you decide what merges.

🤖 多Agent求职系统 | Multi-Agent Job-Search Pipeline — 独立 Python 实现，3 个 AI Agent + 5 道安全护栏 + 工作流编排。支持 MCP 协议接入 OpenCode / Codex / Claude Code。Stan