Havuz

A fast, fully-featured browser and work environment reimagined for you and your agents

Your infinite canvas workspace for agents, tasks, knowledge, and research. An infinite canvas for Claude Code, Codex, terminals, tasks, and

Read it. See it. Get it. Built at GDG AI Hack Milan 2026 for "Learn Different" track.

Your Software Factory - build faster and better with multi node agents that work 24/7

One IDE for you and your AI team. A VS Code fork where Claude Code, Codex, Antigravity, and Muse Code work in parallel across multiple proje

The Juggler Code Agent

A workspace where people and multiple AI agents work together.

useAgent, farklı coding agent’lara ortak workspace, izole computer ortamı ve ekip araçları sunan self-hosted bir çalışma platformudur.

Neden yükseliyor · 29 günde 361 yıldız ve son 28 günde 314 commit dikkat çekiyor; agent’ları ortak bir çalışma ortamı ve gerçek bilgisayar erişimiyle birleştirme fikri güncel bir ihtiyaca hitap ediyor. Ancak commitlerin tek yazardan gelmesi, hareketliliğin geniş katkı veya benimsemeyle desteklendiğini göstermiyor; yükselişin kesin nedeni verilerden bilinmiyor.

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

AI 课程笔记：langchain / langgraph / python / vibe coding

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

Jev-Mem: System-One Controlled Agentic Memory

A Dynamic Island-style command center for managing all your AI coding agents on macOS.

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobil

A control plane so parallel coding agents stop fighting over the same simulator.

Working-draft Mail Action Protocol for agent actions through email, with type contracts, a registry, and a validation CLI.

Embedded agents your customers use to automate work, build views, and connect their tools.

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted A

Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2

Claude Code skill for product videos: real browser capture, branded composition, and local mastering.

ReachAI企业级智能体开发平台：快速、安全完成已有业务系统智能化改造，让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise system

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

WikiSkill, agent oturumlarından kalıcı wiki bilgisi derleyip skill değişikliklerini doğrulama testleriyle kabul veya geri alan bir Python aracıdır.

Neden yükseliyor · Agent'lar için kalıcı bilgi ve self-improvement ilgisinin yüksek olduğu bir dönemde, araştırma makalesindeki döngüyü gerçek agent çalıştırmalarıyla uygulanabilir bir araca dönüştürdüğünü öne sürüyor. 29 günlük yaşına göre 250 yıldız ve son 28 günde 22 commit dikkat çekici; ancak yalnızca 2 farklı yazar var ve yıldızlar kullanım ya da etkinin kanıtı değil.

Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

Event-sourced graph runtime for durable and stateful agents

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

Codex for Android, iOS & Mac. | Aether 扶摇

🐨 The cloud for your team's agents. Save your agent memory, credentials, code, and automations, portable across every agent with Kody.

Kanwas — Shared context board for teams and agents

infinite-creation 是一个通过提交小说/剧本，本地ComfyUI-MiniMaxH3+Agent+Skill技能全自动无限生产视频，不限时长。

Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai

EvoTrace, Claude Code ve Codex oturumlarını inceleyip eğitim, değerlendirme ve doğrulama için yeniden kullanılabilir varlıklara dönüştürür.

Neden yükseliyor · 39 günde 292 yıldız, coding agent oturumlarından eğitim ve değerlendirme varlığı üretme fikrine ilgi olduğunu gösteriyor; ancak bu ilginin nedeni ölçümlerden anlaşılamıyor. Son 28 günde commit ve farklı yazar olmaması, ilginin devam eden geliştirme veya benimsemeyle desteklendiğine dair kanıt sunmuyor.

Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent vi

LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamic

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote fro

shadcn/ui, but for building agents. 🤖

Private control plane for AI agents

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

A keyboard-first diff viewer with LSP support and GitHub integration.

PACT is an open protocol for personal agents to interact with businesses’ agents under explicit, verifiable user permissions.

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif

Build AI Teammates that answer from your own knowledge.

A production-grade agent runtime engineered from the Harness Engineering philosophy.

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

The graph based agentic IDE

groma.md - Your architecture as OKF Markdown in Git, and one C4 map you can walk. Scanned from source, curated by you and your agents.

Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide

Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no dupl

Libra: Efficient Resource Management for Agentic RL Post-Training

KSoR (Knowledge System of Record) is an open-source SDK for building governed, authoritative knowledge systems for humans and AI agents. It