RightNow-AI/openfang
OpenFang is an open-source agent operating system, built in Rust, designed to facilitate the management and orchestration of AI agents.
Awesome AI Agents › AI Agent Operating System
agentlas-ai/Agentlas-OS
Agentlas OS is an agent platform built on the open-source Hephaestus engine that treats an agent as a portable package rather than a setting locked inside one chat or vendor workspace. It separates three activities: building an agent from a plain-language request, borrowing specialist agents from the public Agentlas Hub, and owning the result through a private, owner-scoped Agent Cloud that can restore a package on any signed-in machine. The build pipeline classifies the request, runs an interview and a research gate, generates a package with roles, tools, memory boundaries, permissions, routing and verification contracts, verifies it, then asks whether to keep it only on the local computer or save it to the cloud. Several agents, local or borrowed from the Hub, can be combined into one orchestrator that manages routing, handoffs and review boundaries while roles stay explicit. Execution happens on the host the user already runs, using that host files, tools, credentials and permission rules, with model access through the user own account or API key; listed hosts include Claude Code, Codex, Gemini, Antigravity, Cursor, DeepSeek, GLM and Ollama. A desktop application provides a dashboard over local agents, cloud storage, Hub specialists, connected model hosts and automations. Installation is offered through a shell installer that also sets up host command adapters and a marketplace plugin, exposing a command surface inside the host; the README additionally contains a block of text written to be pasted into an LLM so it performs the installation, which is instruction text aimed at an assistant rather than a described feature. The documented Agent Trust contract covers portable, inspectable and restorable packages. The project is Apache-2.0 licensed with README translations in Korean, Chinese, Japanese and Hindi.
https://github.com/agentlas-ai/Agentlas-OS
Also in AI Agent Operating System
Arindam200/awesome-ai-apps
A comprehensive repository showcasing practical examples, tutorials, and tools for building powerful AI applications using large language models and various AI agent frameworks.
OpenByteInc/QuantDinger
QuantDinger is an open-source AI trading operating system designed for independent traders, Python strategy authors, and small teams, offering backtesting, live trading, and multi-agent research ca...
MemTensor/MemOS
MemOS is an operating system for Large Language Models that enhances their capabilities with long-term memory, enabling more context-aware, consistent, and personalized AI interactions through a modular and extensible memory architecture.
holaboss-ai/holaOS
HolaOS is a local-first, AI-powered desktop agent that learns your work context, integrates with over 100 workplace tools, and manages memory efficiently to provide proactive assistance without for...
mcp-use/mcp-use
mcp-use is an open-source unified client library that enables seamless integration of any LangChain-supported LLM with MCP servers to build custom agents with tool access.
astrid-runtime/astrid
Astrid is a portable, capability-secure operating system for composable software components, providing an OS-grade boundary for AI agents and other untrusted code via WebAssembly capsules.
HKUDS/AutoAgent
AutoAgent is a fully-automated, zero-code framework for creating and deploying LLM agents using natural language, featuring top GAIA benchmark performance and broad LLM support.