Awesome AI Agents › AI Agent Operating System

vastsa/PI-Desktop

⭐ 7801 TypeScript added to this list on 2026-09-28 repository created 2023-03-22

PI-Desktop is a desktop workspace aimed specifically at hosting AI agents outside the confines of a terminal or code editor. Its stated premise is that terminal agents are strong at execution and IDE-embedded agents are strong at living inside an editor, but neither gives an agent a persistent, independent environment of its own; PI-Desktop tries to fill that gap by presenting projects, agent sessions, code reviews, live previews and the agents themselves as first-class objects inside one always-available desktop application. It is model-agnostic, meaning it is designed to work with different underlying language models and agent backends rather than being tied to one provider, and it is local-first, keeping a user's projects on their own machine rather than requiring a hosted service. Its architecture is explicitly plugin-powered: third-party plugins can extend what the workspace does, and the project documents how to build a plugin alongside its user-facing guide and screenshots. It ships prebuilt releases for macOS, Windows and Linux and is currently in an early-preview 0.15.x release line, with an active GitHub Actions CI pipeline and MIT-style licensing information in the repository. The interface layout described in its documentation organizes work into an 'independent workspace' concept (with no dependency on a specific IDE or terminal) alongside the plugin system, so a session, review or preview persists inside the desktop app rather than being scoped to a single terminal window or editor tab. As a category it functions as agent-hosting infrastructure and a graphical control surface, comparable to other desktop shells built around coding and chat agents, but oriented around treating the desktop workspace itself as the durable, extensible unit rather than any one agent or model.

https://github.com/vastsa/PI-Desktop

desktop-appagent-workspaceplugin-systemlocal-firstmodel-agnostic

Also in AI Agent Operating System

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.

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.