跳到主要内容

Welcome to OpenHuman

OpenHuman is an open-source AI assistant designed to be the memory and doer for everything you do across your tools. Built on Rust + Tauri and licensed under GNU GPL3, it closes the gap between what AI models can do and what they actually know about you.

Every model in the world, all 200+ of them, shares the same fundamental limitation: they are stateless. You type a prompt, get a response, and the context evaporates. Even the ones with "memory" store a few bullet points. A few bullet points is a sticky note, not intelligence.

OpenHuman solves this with a stack that's calmly, deliberately different:

  • A local-first Memory Tree. Every source you connect. Gmail, Slack, GitHub, Notion, your own notes, flows through a deterministic pipeline: canonical Markdown, ≤3k-token chunks, scored, folded into per-source / per-topic / per-day summary trees. Stored in SQLite on your machine. No vector-soup black box.
  • An Obsidian-style wiki on top of it. The same chunks the agent reasons over land as .md files in a vault you can open in Obsidian, browse, edit, and link by hand. Inspired by Karpathy's obsidian-wiki workflow. You can't trust a memory you can't read.
  • 118+ third-party integrations. One-click OAuth into Gmail, GitHub, Slack, Notion, Stripe, Calendar, Drive, Linear, Jira and more - no API keys to wire by hand, no plugin marketplace to navigate.
  • Auto-fetch. Every twenty minutes, OpenHuman pulls fresh data from every active connection and folds it into the Memory Tree without you asking, so the agent already has tomorrow's context this morning.
  • An agent built for big data. Smart token compression (TokenJuice) compacts verbose tool output before it ever enters the model's context, so sweeping through your last six months of email costs single-digit dollars. Automatic model routing sends each task to the right model.
  • Batteries included. A complete agent toolbelt is wired in by default: web search, web-fetch scraper, a full coder toolset (filesystem, git, lint, test, grep), browser & computer control, cron & scheduling, memory tools, agent coordination, and native voice.
  • Simple, UI-first. A clean desktop experience and short onboarding paths take you from install to a working agent in a few clicks - no config-first setup, no terminal required.

Together, these turn OpenHuman into something fundamentally different from a chatbot. It is an AI agent that consumes large amounts of personal data at low cost, maintains a persistent and evolving understanding of your world, and takes proactive actions on your behalf.

OpenHuman is not AGI. But it is a meaningful architectural step closer, with better memory, better orchestration, and better tooling.

Key Features​

  • Memory Tree: Local-first knowledge base with deterministic pipeline
  • Obsidian-Style Wiki: Every memory chunk also lives as a Markdown file
  • 118+ Integrations: Gmail, Notion, GitHub, Slack, Stripe, Calendar and more
  • Auto-fetch: Every 20 minutes, data is pulled into your memory tree
  • Smart Token Compression: TokenJuice keeps large data handling affordable
  • Automatic Model Routing: Tasks pick their model via hint prefixes
  • Meeting Agents: Mascot joins Google Meet as a real participant
  • Native Voice: Speech-to-text in, text-to-speech out

Join the Community​

OpenHuman is in early beta. Feedback and contributions make a real difference at this stage.