Sàn agent

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

Experts.js is the easiest way to create and deploy OpenAI's Assistants and link them together as Tools to create advanced Multi AI Agent Systems with expanded memory and attention to detail.

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

Latest Advances on Agentic AI & AI Agents for Healthcare

LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent, using dual-graph reasoning.

An autonomous agent that takes work, does work, gets paid, and gets better at it.

A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

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

TypeScript AI AI Function Calling Framework enhanced by compiler skills.

Multi-Agent Framework

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

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

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

📚 Real-world OpenClaw automation examples from Moltbook

[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems

A security scanner for your LLM agentic workflows

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

Hexabot v3 is an AI automation platform, combining workflows, actions, agents, and conversational channels in one runtime.

Awesome Game AI materials of Multi-Agent Reinforcement Learning

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

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.

Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your phone. One pip install, zero infrastructure. A production‑minded orchestrator for 24/7 workflow

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

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