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
Sleepless Agent is a long-running daemon that drives the Claude Code CLI through the Python Agent SDK so that queued work continues while the user is away. Tasks arrive either through Slack slash commands or through the local sle command line tool, are stored in a SQLite-backed persistent queue, and are executed one by one with priority-aware scheduling. Each task runs in its own isolated workspace, so several tasks can proceed in parallel without interfering with each other, and every output is stored with metadata for later reference. The project separates two kinds of input: casual thoughts, whose results are applied automatically, and serious project tasks, which are attached to a named project and held for review. Git integration commits the work on a feature branch and, when the gh CLI is available, opens a pull request, so results arrive as reviewable changes rather than as chat transcripts. The CLI exposes daemon control, task submission, queue and usage status, cancellation, report viewing and a trash with restore. Slack adds the same operations as slash commands (/think, /chat, /check, /usage, /cancel, /report, /trash) plus an interactive chat mode that holds a conversational session inside a Slack thread, and it requires an app in Socket Mode with bot scopes for messages, commands, mentions, channel history and reactions. Slack is optional; every feature is reachable from the CLI alone. Usage thresholds are configured separately for day and night so that the daemon spends subscription capacity mainly during idle hours. Requirements are Python 3.11 or newer, the Claude Code CLI authenticated once via claude login, Git, and optionally the gh CLI. It installs from PyPI as sleepless-agent.
https://github.com/context-machine-lab/sleepless-agent
OpenFang is an open-source agent operating system, built in Rust, designed to facilitate the management and orchestration of AI agents.
A comprehensive repository showcasing practical examples, tutorials, and tools for building powerful AI applications using large language models and various AI agent frameworks.
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...
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.
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 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 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.
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.