Agents

Open-source personal AI assistant that runs on your own hardware and answers in the chat apps you already use

Open-source personal assistant that uses tools, memory and local or remote AI providers to carry out tasks

Open-source, self-hosted AI agent platform for persistent bots with their own computers and memory.

Open-source terminal AI agent that runs shell, Python and web tools on any model, including local ones.

Open-source single-binary personal agent server in Rust with sandboxed commands and chat channels.

Local bot builder that turns repeated work into scheduled microapps, with an approval gate on every external action.

Personal AI assistant with eight memory types, hourly proactive check-ins and channels from macOS and iOS to Slack and Telegram.

Windows desktop AI companion built on Electron with a Live2D character, long-term memory, voice and tool calling.

Native macOS AI agent that connects many LLM providers to a task loop that drives apps through Accessibility and builds in Xcode.

Desktop AI assistant with a Live2D avatar, knowledge-graph memory, voice, MCP and skills, under AGPL-3.0 or a commercial license.

Open-source personal AI for macOS that builds an on-device understanding of your work and can take over tasks with its own cursor.

Open-source desktop agent combining real-time voice chat, a speaking character and delegated work with visible permissions.

Voice-activated LLM agent for Raspberry Pi that runs Ollama models fully on the device and can run custom tools.

Open-source Mac personal AI that works through your Claude Code or Codex CLI session, with voice, screen awareness and phone calls.