Sàn agent

OpenAgents - AI Agent Networks for Open Collaboration

Maestro: Netflix’s Workflow Orchestrator

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

A system for agentic LLM-powered data processing and ETL

Curated list of the best truly open-source AI projects, models, tools, and infrastructure.

A curated list of awesome skills, tools, integrations, and resources for Hermes Agent by Nous Research

A library of reinforcement learning components and agents

CADAM is the open source text-to-CAD web application

One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.

AI Agent Orchestration Dashboard - Manage AI agents, assign tasks, and coordinate multi-agent collaboration via OpenClaw Gateway.

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.

Technical resources for AI developers to build applications, agents, and systems using Oracle AI Database and OCI services

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

Examples and tutorials to help developers build AI systems

GenAI Cookbook

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

An open source extension that connects AI agents to computational notebooks in JupyterLab.

⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit

Modular SenseNova skills for building AI-powered office assistants and productivity workflows

CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.