kortix-ai/CompanyOS
Open-source, cloud-native agent harness that runs always-on, event-driven agents for a company -- triggered by schedules, webhooks or messages, running in parallel with shared memory and state.
Awesome AI Agents › AI Agent Operating System
makecindy/cindy
Cindy is an open-source client for a general-purpose AI agent designed to run locally on a user's own machine and act across their real files and logged-in applications. Rather than being a single model wrapper, Cindy sits above multiple underlying agent harnesses, starting with Claude Code and Codex and with more planned, and lets the user mix models and harnesses freely, even switching mid-task, while the workspace, conversation memory, learned skills and connected tools remain continuous across that switch. A single task can be planned by one harness/model combination, executed in parallel across several, and reviewed by yet another, which the project frames as a way to get the complementary strengths of different coding agents without re-establishing context each time. Beyond coding tasks, Cindy can drive a browser, the local computer and, through the mobile apps, a phone, and it can pick up work triggered from instant messaging or on a schedule. The repository is the open-source client: the desktop and mobile apps and their shared packages, organized as a pnpm monorepo, licensed Apache-2.0. Users can connect existing Claude Code or Codex coding-plan subscriptions, bring their own API keys, run local models, or sign in to the official hosted Cindy service with usage billed transparently. The "yours to shape" framing emphasizes that corrections to memory persist across harnesses, skills taught once are reusable, and recurring work can be scheduled to run and report back on its own. Linux is supported with a dedicated installation guide for Ubuntu, Arch and Omarchy. The project targets developers and power users who already rely on terminal coding agents and want one persistent, extensible agent identity spanning multiple models and surfaces instead of separate sessions per tool.
https://github.com/makecindy/cindy
Also in AI Agent Operating System
RightNow-AI/openfang
OpenFang is an open-source agent operating system, built in Rust, designed to facilitate the management and orchestration of AI agents.
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.