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
holaboss-ai/holaOS
HolaOS is presented as a 'super agent for work' designed to operate locally first, meaning data and memory remain on the user's computer, enhancing privacy and control. It integrates with more than 100 workplace applications such as Linear, GitHub, Slack, Jira, HubSpot, and Gmail, allowing it to automatically fetch relevant information and understand the user's working context in minutes. A core feature is its sophisticated Memory Management System, which includes a local-first knowledge base built from workspace files, browser state, and integration data. This memory is stored as Markdown, embedded with SQLite vec, and retrieved using RAG (Retrieval-Augmented Generation) to ensure the agent never 'forgets' past work and can recall relevant context quickly. The system employs a 'Session Context Compression' mechanism to maintain fresh reasoning capabilities while preserving historical context efficiently, preventing the "slow drift into bloated, expensive, fragile sessions" common in long-running agents. This allows approximately 70% of the model's token window to be reserved for current tasks, with older history intelligently compressed and checkpointed. HolaOS offers a user-friendly desktop application interface, eliminating the need for command-line interaction and centralized management of tasks, files, and agent interactions. It also supports hidden subagents for parallel processing of complex tasks, and integrates with a user's browser profile for broader web-based work. The project emphasizes user control over stored memory, allowing users to view, edit, and remove information, ensuring transparency and ownership.
https://github.com/holaboss-ai/holaOS
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.
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.
Q00/ouroboros
Ouroboros is an Agent OS for AI coding, providing a local-first runtime layer to transform non-deterministic agent work into replayable, observable, and policy-bound execution contracts.