Sàn agent

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

An agentic workflow tool that provides context engineering support for opencode

A curated list of awesome AGI frameworks, software and resources

The first agentic payment network: policy-controlled, gasless, and real money-ready. OmniClaw CLI + Financial Policy Engine let autonomous agents pay and earn safely at machine speed.

Leash by StrongDM - take your AI agents for a walk

Simple to install, powerful command-line based AI agent system for coding.

Personal-Model First Self Evolving AI Agent 🐘

A decentralized agent network for building collaborative, LLM-powered agent-to-agent (A2A) systems.

GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

A swarm of disposable agents for unattributable web interaction. The user never acts on the web directly, delegating instead to agents that are destroyed on completion, leaving nothing that leads back.

Offical Implementation for "Recursive Multi-Agent Systems"

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

AI agents that guide you from idea to working code, with you in control at every step.

Universal AI Agent Frontend. Build your backend we handle the rest.

A distributed framework for LLM agents

Self-evolving second brain with 17 AI skills, 6 worker agents, and people CRM — inspired by Garry Tan's gstack and gbrain. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

👩🏻‍🍳 A collection of example notebooks using Haystack

Open workflow intelligence for discovering, validating, repairing, and generating automation workflows across frameworks — starting with n8n.

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

The Coordination Layer for Multi-Agent AI