Havuz

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

[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

The Juggler Code Agent

Private control plane for AI agents

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

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

Agents Office v3 (Beta) — a headless office where AI agents do real work

Codex for Android, iOS & Mac. | Aether 扶摇

Kanwas — Shared context board for teams and agents

Event-sourced graph runtime for durable and stateful agents

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

#1 open-source code reviewer on Code-Review-Bench

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

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

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

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

FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs

Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

shadcn/ui, but for building agents. 🤖

Agentspan is now part of Orkes Conductor

Open source AI company OS. 38 roles, 6 templates, 4-layer memory. Your AI company remembers everything — locally. npx clawcompany

Control your Pi coding agent from your phone. Pair with a one-time QR code and chat with your local agent, even when you're away from your c

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Your First LLM-Wiki Conversation Knowledge Base

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

A workspace where people and multiple AI agents work together.

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it

Open Source Agentic Security Scanner

Change Risk Anti-Patterns (CRAP) metric for Rust projects

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a

Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily,

Outworked - Cozy Office for Claude Code

ИИ-девушка с человеческим поведением: сон, настроение, расписание, память, стадии отношений и конфликты. Userbot mode через MTProto — реагир

The missing bridge between your ML models and your AI agents.

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, les

Agentic SEO / Agentic Engine Optimization (AEO) tools

A curated list of code samples and tutorials for building agents on Gemini Enterprise Agent Platform (previously Vertex AI).

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

A programmable tool and agent runtime for Pi

ClickClackClaw - The chat app with claws.

The graph based agentic IDE

Libra: Efficient Resource Management for Agentic RL Post-Training

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

🪞 Make your agents recursively self-improve

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

Unified Agentic AI and Data Platform

Build AI Teammates that answer from your own knowledge.

AI驱动的一站式论文搜集、写作、精读论文、协同助写方案

Monet — Multi-engine mission control for coding agents (Claude Code and Codex today). Browse, search, and drive your agent sessions from a n

Ridiculous speed. Readable code.