# OpenHuman ## πŸ‡ΊπŸ‡Έ/πŸ‡¬πŸ‡§ English - [Welcome to OpenHuman](https://tinyhumans.gitbook.io/openhuman/overview/readme.md): Personal AI super intelligence for your desktop: a brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher across 118+ connec - [Getting Started](https://tinyhumans.gitbook.io/openhuman/overview/getting-started.md): Install OpenHuman, walk through the in-app onboarding (sign in, connect Gmail, choose how AI runs), and run your first request against your own Memory Tree. - [Troubleshooting Sign-In](https://tinyhumans.gitbook.io/openhuman/overview/troubleshooting-sign-in.md): Diagnose sign-in failures, OAuth callbacks that do not complete, and remote core RPC authentication problems. - [Guides](https://tinyhumans.gitbook.io/openhuman/guides/guides.md): Outcome-driven, step-by-step guides for getting a real result out of OpenHuman: set up an assistant, run a local model, protect sensitive data, recover a broken install, or move to a new machine. - [Create my personal AI assistant](https://tinyhumans.gitbook.io/openhuman/guides/guides/personal-assistant.md): Go from a fresh install to a working personal assistant that knows your context, respects your boundaries, and acts only with your approval. - [Use OpenHuman with a local model](https://tinyhumans.gitbook.io/openhuman/guides/guides/local-model.md): Run OpenHuman's inference on your own machine with Ollama: detection, model selection, a real test, and every way it commonly breaks with the fix. - [Keep sensitive data private](https://tinyhumans.gitbook.io/openhuman/guides/guides/privacy-sensitive-data.md): A plain-language map of what OpenHuman keeps on your computer versus what it sends out, and the settings that let you keep sensitive work local. - [Recover from a failed installation](https://tinyhumans.gitbook.io/openhuman/guides/guides/recover-failed-installation.md): Get a broken or half-installed OpenHuman running again without losing your memory, personas, or settings. Configuration is preserved by default. - [Move OpenHuman to a new PC](https://tinyhumans.gitbook.io/openhuman/guides/guides/move-to-new-pc.md): Carry your OpenHuman persona, memory, workspace, and model/provider config to a new computer, and understand which secrets travel and which you re-enter. - [Connect OpenHuman to Obsidian](https://tinyhumans.gitbook.io/openhuman/guides/guides/connect-obsidian.md): Open OpenHuman's memory as an Obsidian vault so you can read, edit, and link the agent's notes by hand, and have it pick up your edits. - [Organize my project folders](https://tinyhumans.gitbook.io/openhuman/guides/guides/organize-project-folders.md): Let OpenHuman tidy, rename, and restructure a folder of files safely, inside a boundary you set, with every change gated by your approval. - [Create a doctor-specific assistant](https://tinyhumans.gitbook.io/openhuman/guides/guides/doctor-assistant.md): Shape OpenHuman into a role-specific assistant for clinical work: persona, tight data boundaries, and the limits you must keep in mind. - [Create a safe companion for a child](https://tinyhumans.gitbook.io/openhuman/guides/guides/child-safe-companion.md): Compose OpenHuman's autonomy, approval, and content-screening controls into a locked-down assistant for a child, with an honest account of the limits. - [Realtime Mascot](https://tinyhumans.gitbook.io/openhuman/features/mascot.md): The on-screen face of OpenHuman, a desktop mascot that speaks, reacts, joins your meetings, and thinks in the background even when you aren't looking at it. - [Meeting Agents](https://tinyhumans.gitbook.io/openhuman/features/mascot/meeting-agents.md): The mascot joins Google Meet, Zoom, Teams, and Webex as a real participant: listens, streams a live transcript, speaks back when addressed, auto-joins from your calendar, and uses tools mid-meeting. M - [Memory](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki.md): Every memory chunk also lives as a Markdown file in an Obsidian-compatible vault you can open and edit. Inspired by Karpathy's obsidian-wiki workflow. - [Memory Tree](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/memory-tree.md): OpenHuman's local-first knowledge base. Ingest from your tools, canonicalize into Markdown, chunk, score, and fold into hierarchical summary trees. - [Memory Sources & Scoping](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/sources.md): The typed registry of connectors that feed your Memory Tree (local folders, GitHub repos, RSS feeds, web pages, and Composio OAuth integrations), plus per-agent source scoping for privacy and focus. - [Auto-fetch from Integrations](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/auto-fetch.md): Every twenty minutes, OpenHuman walks every active integration and folds new data into your memory tree. No prompts, no polling loops you have to write. - [Scoring & Ranking](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/scoring.md): How OpenHuman scores every chunk before it enters the Memory Tree - weighted signals gate admission, entity extraction enriches it, and an inverted index plus vector embeddings make it recallable. - [Retrieval & Recall](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/retrieval.md): How OpenHuman reads back from the memory tree. A handful of deterministic retrieval primitives, canonical entity resolution, a co-occurrence graph, and a specialist memory sub-agent that combines them - [Memory Diff (Git-Backed)](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/memory-diff.md): Git-backed change tracking for memory. Every sync is committed to a snapshot ledger, so the agent can ask "what changed since I last looked?" - [agentmemory backend](https://tinyhumans.gitbook.io/openhuman/features/obsidian-wiki/agentmemory-backend.md): Optional \`Memory\` trait backend that delegates to a locally-running agentmemory REST server, for users who self-host agentmemory across Claude Code, Cursor, Codex, OpenCode, and OpenHuman. - [Third-party Integrations (118+)](https://tinyhumans.gitbook.io/openhuman/features/integrations.md): 118+ third-party integrations - Gmail, Notion, GitHub, Slack, Stripe, Calendar and more - with one-click OAuth and zero API keys. - [Triggers](https://tinyhumans.gitbook.io/openhuman/features/integrations/triggers.md): Live events from connected integrations (a new Gmail message, a Notion edit, a Stripe charge) arrive as triggers, get classified by a triage agent, and can fire agent actions automatically. - [MCP Servers & Skills](https://tinyhumans.gitbook.io/openhuman/features/integrations/mcp-and-skills.md): Beyond the curated OAuth connectors - browse thousands of MCP servers and a 90,000-entry Skills catalog, and let OpenHuman act as an MCP server itself. - [The Orchestrator](https://tinyhumans.gitbook.io/openhuman/features/orchestration.md): OpenHuman is an orchestrator, not a chatbot: durable agent graphs, visual workflows, sub-agent fleets, a split-brain always-on layer, and end-to-end encrypted agent-to-agent sessions, all in one coher - [Workflows](https://tinyhumans.gitbook.io/openhuman/features/workflows.md): Durable, visual automations built on the open-source tinyflows engine. The agent proposes a workflow in chat; you review it on a canvas, save it, and it runs on schedules or live app events, pausing f - [Messaging Channels](https://tinyhumans.gitbook.io/openhuman/features/channels.md): Messaging platforms OpenHuman talks back to you on: inbound dispatch into the agent loop, outbound replies and proactive delivery, and per-channel credentials. - [SuperContext](https://tinyhumans.gitbook.io/openhuman/features/super-context.md): Deterministic, harness-driven context preparation on the first turn of every new conversation - so the agent never starts cold. - [Goals & Todos](https://tinyhumans.gitbook.io/openhuman/features/goals-and-todos.md): Long-term goals, per-thread objectives with budgets, and a kanban task board - how OpenHuman stays pointed at what matters. - [Personalization & Self-Learning](https://tinyhumans.gitbook.io/openhuman/features/personalization.md): How OpenHuman learns your communication style, identity, tooling, vetoes, and goals from everyday use, then surfaces them as ambient defaults in every reply. - [Themes & Theme Studio](https://tinyhumans.gitbook.io/openhuman/features/theming.md): Five built-in theme families, light/dark/auto variants, and a full visual Theme Studio - make OpenHuman look the way you want. - [Smart Token Compression](https://tinyhumans.gitbook.io/openhuman/features/token-compression.md): TokenJuice - a multi-stage compression router that compacts verbose tool output before it ever enters LLM context. - [Automatic Model Routing](https://tinyhumans.gitbook.io/openhuman/features/model-routing.md): One subscription, many models. Tasks pick their model via hint prefixes: reasoning goes to a strong model, fast paths go to a fast one, vision to vision. - [Local AI (optional)](https://tinyhumans.gitbook.io/openhuman/features/model-routing/local-ai.md): Optional, opt-in local AI via Ollama or LM Studio. Powers memory embeddings, summary-tree building, background loops, and explicitly routed chat/reasoning workloads on-device. - [Available Tools](https://tinyhumans.gitbook.io/openhuman/features/native-tools.md): The full toolset OpenHuman's agent has out of the box - research, code, control your machine, schedule jobs, talk back to you, and call into 118+ third-party services. - [Web Search](https://tinyhumans.gitbook.io/openhuman/features/native-tools/web-search.md): A native search tool the agent can call directly - no API key required. - [Image Tools](https://tinyhumans.gitbook.io/openhuman/features/native-tools/image-tools.md) - [Web Scraper](https://tinyhumans.gitbook.io/openhuman/features/native-tools/web-scraper.md): A purpose-built "GET-and-read" tool that returns clean text, not raw HTML. - [Image & Video Generation](https://tinyhumans.gitbook.io/openhuman/features/native-tools/media-generation.md): Ask for an image or a video and dedicated media agents generate it: image generation and editing (Seedream / SeedEdit), plus text-to-video and animate-a-reference-image (Seedance / Veo), saved straigh - [Coder](https://tinyhumans.gitbook.io/openhuman/features/native-tools/coder.md): A complete toolset for working on real codebases - read, write, edit, search, git, lint, test. - [Browser & Computer Control](https://tinyhumans.gitbook.io/openhuman/features/native-tools/browser-and-computer.md): Open URLs, take screenshots, click, type, and move the mouse - natively. - [Cron & Scheduling](https://tinyhumans.gitbook.io/openhuman/features/native-tools/cron.md): Recurring jobs, one-off reminders, and scheduled agent runs - first-class. - [Voice](https://tinyhumans.gitbook.io/openhuman/features/native-tools/voice.md): Native voice - speech-to-text in, text-to-speech out, mascot lip-sync, and a live Google Meet agent that listens and speaks. - [Memory Tools](https://tinyhumans.gitbook.io/openhuman/features/native-tools/memory-tools.md): How the agent reads, writes, and searches its own long-term memory. - [Tool-Scoped Memory](https://tinyhumans.gitbook.io/openhuman/features/native-tools/tool-memory.md): Durable, tool-scoped rules for safety-critical guidance and learnings. - [Third-party Integrations](https://tinyhumans.gitbook.io/openhuman/features/native-tools/integrations.md): The agent's view of the 119+ connected third-party services. - [Agent Coordination](https://tinyhumans.gitbook.io/openhuman/features/native-tools/agent-coordination.md): Tools the agent uses to plan, delegate, and ask for help. - [System & Utilities](https://tinyhumans.gitbook.io/openhuman/features/native-tools/system-and-utilities.md): Shell, node, SQL, current time, push notifications - the small tools that round out the toolbelt. - [Subconscious Loop](https://tinyhumans.gitbook.io/openhuman/features/subconscious.md): Background loop that evaluates user / system tasks against the workspace and decides what to do. - [Notifications & Activity](https://tinyhumans.gitbook.io/openhuman/features/notifications-and-activity.md): The notification center, the Activity transparency hub, and the Routines scheduler: everything OpenHuman tells you about, and everything it does in the background. - [Screen Intelligence](https://tinyhumans.gitbook.io/openhuman/features/screen-intelligence.md): On-device screen capture, OCR + vision summarization, input automation, and inline autocomplete, gated behind explicit macOS privacy permissions. - [Wallet](https://tinyhumans.gitbook.io/openhuman/features/wallet.md): Local, non-custodial multi-chain crypto wallet the agent can read balances from and send transfers with. Keys stay in-core and never cross the wire. - [tiny.place Agent Economy](https://tinyhumans.gitbook.io/openhuman/features/tinyplace.md): Your agent is a citizen of tiny.place, the agent-to-agent social economy. Register a @handle, message other agents over Signal-protocol E2E encryption, post and win x402 USDC bounties, and trade in th - [Billing, Cost & Usage](https://tinyhumans.gitbook.io/openhuman/features/billing-and-usage.md): Plans, credits and saved cards over Stripe and Coinbase, plus a local real-time dashboard for token usage, cost and budget enforcement. - [Rewards & Referrals](https://tinyhumans.gitbook.io/openhuman/features/rewards-and-referrals.md): Invite friends, earn referral credit, redeem promo codes, and unlock Discord community roles - the in-app Rewards & Referrals surface. - [iOS Companion](https://tinyhumans.gitbook.io/openhuman/features/ios-companion.md): Pair an iOS companion app to your desktop OpenHuman over an end-to-end encrypted tunnel, scanned from a QR code. - [Approval Gate](https://tinyhumans.gitbook.io/openhuman/features/approval-gate.md): Human-in-the-loop consent for side-effecting tool calls. The agent parks any risky action until you approve it, and fails closed if you don't. - [Privacy & Security](https://tinyhumans.gitbook.io/openhuman/features/privacy-and-security.md) - [Privacy Mode](https://tinyhumans.gitbook.io/openhuman/features/privacy-and-security/privacy-mode.md): One switch, enforced in the Rust core: local-only mode blocks every cloud model call and permits only on-device runtimes (Ollama, LM Studio, MLX, local OpenAI-compatible endpoints). - [OS Keyring & Secret Storage](https://tinyhumans.gitbook.io/openhuman/features/privacy-and-security/os-keyring-and-secret-storage.md) - [Platform & Availability](https://tinyhumans.gitbook.io/openhuman/features/platform.md): What OpenHuman ships as (native React + Tauri v2 desktop app with a Rust core), supported platforms, and what's in scope today. - [Cloud Deploy](https://tinyhumans.gitbook.io/openhuman/features/cloud-deploy.md): Hosting the headless openhuman-core in the cloud - DigitalOcean App Platform, Fly.io, or Docker Compose on any VPS. - [Overview](https://tinyhumans.gitbook.io/openhuman/developing/developing.md): Build, run, test, and ship OpenHuman from source. - [Getting Set Up](https://tinyhumans.gitbook.io/openhuman/developing/getting-set-up.md): How to build OpenHuman from source - toolchain, vendored Tauri CLI, and local desktop builds. - [Building the Rust Core](https://tinyhumans.gitbook.io/openhuman/developing/building-rust-core.md): Build the Rust core from scratch on a fresh machine. - [Testing Strategy](https://tinyhumans.gitbook.io/openhuman/developing/testing-strategy.md): How OpenHuman tests its product - Vitest, cargo test, WDIO E2E. Where each test goes. - [E2E Testing](https://tinyhumans.gitbook.io/openhuman/developing/e2e-testing.md): End-to-end testing with WDIO + Appium. CI and local setup. - [Release Policy](https://tinyhumans.gitbook.io/openhuman/developing/release-policy.md): Release cadence, version policy, OAuth-and-installer rules. How shipping works. - [Polymarket Integration (v1 Read + Trading)](https://tinyhumans.gitbook.io/openhuman/developing/polymarket.md) - [Chromium Embedded Framework](https://tinyhumans.gitbook.io/openhuman/developing/cef.md): Why OpenHuman ships its own Chromium runtime, what we use it for today, and what the same CDP surface unlocks next. - [Theming (Token System)](https://tinyhumans.gitbook.io/openhuman/developing/theming.md) - [Agent Observability](https://tinyhumans.gitbook.io/openhuman/developing/agent-observability.md): Artifact-capture layer that makes E2E tests debuggable. Logs, traces, screenshots. - [Architecture](https://tinyhumans.gitbook.io/openhuman/developing/architecture.md): High-level shape of the OpenHuman system (desktop shell, Rust core, Memory Tree, agent loop). Pointer to the deep developer architecture in the repo. - [Agent Harness](https://tinyhumans.gitbook.io/openhuman/developing/architecture/agent-harness.md): How an agent turn actually runs - the tool-call loop, sub-agent dispatch, archetypes, triage, hooks, and the cost/budget machinery around them. - [Flows on TinyAgents (src/openhuman/flows/)](https://tinyhumans.gitbook.io/openhuman/developing/architecture/flows-on-tinyagents.md): How a saved flow runs - lowering a WorkflowGraph onto tinyagents, the {run,nodes} run-state, the capability seam, agent-nodes-as-nested-graphs, the two-layer security model, and the one-trigger model. - [Memory Tree (src/openhuman/memory\_tree/)](https://tinyhumans.gitbook.io/openhuman/developing/architecture/memory-tree.md): The generic summary-tree engine under the Memory Tree feature - bucket-seal cascades, scoring, embedding, entity extraction, retrieval, summarisation. Kind-agnostic mechanics for the Source trees (the - [MCP Registry (src/openhuman/mcp\_registry/)](https://tinyhumans.gitbook.io/openhuman/developing/architecture/mcp-registry.md): The dynamic, user-facing side of MCP-client support: discover servers on Smithery and the official MCP registry, persist installs to SQLite, supervise local-spawn subprocess lifecycle, surface their t - [Security (src/openhuman/security/)](https://tinyhumans.gitbook.io/openhuman/developing/architecture/security.md): Trust boundary for the autonomous core - autonomy / risk policy, pluggable sandbox backends (Docker, Bubblewrap, Firejail, Landlock, Noop), audit log, encrypted secret store, public-bind / pairing gua - [Frontend (app/src/)](https://tinyhumans.gitbook.io/openhuman/developing/architecture/frontend.md): The React + Vite frontend (\`app/src/\`) - architecture, state, services, providers, routing, components, hooks. - [Tauri Shell (app/src-tauri/)](https://tinyhumans.gitbook.io/openhuman/developing/architecture/tauri-shell.md): The desktop host (\`app/src-tauri/\`) - Tauri v2 + WebView, IPC, embedded core lifecycle, core bridge. - [Terms & Conditions](https://tinyhumans.gitbook.io/openhuman/legal/terms-of-use.md): Terms and conditions governing use of the OpenHuman service. - [Privacy Policy](https://tinyhumans.gitbook.io/openhuman/legal/privacy-policy.md): How OpenHuman collects, uses, processes, stores, and protects information when you use the service.