Sàn agent

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

Open-source graph database superpowers for your existing Postgres data.

TypeScript AI AI Function Calling Framework enhanced by compiler skills.

🐝 The First Self-Improving agents with RL / Prompting Optimization

Agentic Development skills behind the JS Mastery workflow

The batteries-included, No-Code FinOps automation platform, with the AI you trust.

Open-source alternative to Claude Agent SDK, ChatGPT Agents, and Manus.

MCP server for Google Ads, Meta Ads & GA4 — works with ChatGPT, Claude, Cursor, n8n, Windsurf & more. 250+ tools for campaign management, analytics & optimization.

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdbot) — open-source self-hosted AI agent for WhatsApp, Telegram, Discord & 50+ integrations.

📚 Real-world OpenClaw automation examples from Moltbook

from vibe coding to agentic engineering - practice makes codex perfect

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

MindMemOS

An Open-Source AI Writing Project.

Awesome Game AI materials of Multi-Agent Reinforcement Learning

A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdbot) — open-source self-hosted AI agent for WhatsApp, Telegram, Discord & 50+ integrations.

AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.

构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.

Autonomous AI pentesting engine across web, cloud, identity, CI/CD, IaC, databases, Active Directory, Kubernetes, IoT firmware and AI/LLM endpoints (OWASP LLM Top 10). Real exploits with proof for every finding. Privacy gateway: the LLM never sees your real IPs, hosts or creds; nothing leaves your perimeter.

The all-in-one AI agent living in your terminal. Build landing, mobile apps, backends, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels.

Offical Implementation for "Recursive Multi-Agent Systems"