The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
Rust agent-orchestrationai-agentsai-assistantdesktopllmlocal-firstmcppersonal-aiprivacyrustsecond-braintauri
Table of contents
Overview
Guides
- Guides
- Create my personal AI assistant
- Use OpenHuman with a local model
- Use multiple local LLM servers
- Keep sensitive data private
- Recover from a failed installation
- Move OpenHuman to a new PC
- Organize my project folders
- Create a doctor-specific assistant
- Run health diagnostics
- Create a safe companion for a child
Features
- Chat
- Memory
- Connections
- Settings
- The Mascot
- Third-party Integrations
- The Orchestrator
- Workflows
- Messaging Channels
- Goals & Todos
- Personalization & Self-Learning
- Themes & Theme Studio
- Smart Token Compression
- Automatic Model Routing
- Native Tools
- Notifications & Activity
- Wallet
- Hosting
- Billing, Cost & Usage
- iOS Companion
- Approval Gate
- Privacy & Security
- Platform & Availability
- Cloud Deploy
Developing
- Overview
- Rust Quickstart
- Getting Set Up
- Architecture
- Building the Rust Core
- Loadable modules
- Performance and footprint
- Pluggable engines
- Components
- Jev
- Embedding
- SaaS profiles
- One TinyHumans API key
- Hooks
- MCP Server
- Claude Code CLI provider
- TinyComputer browser on Linux and Docker
- Theming (Token System)
- Testing Strategy
- E2E Testing
- Agent Observability
- Release Policy
- AgentBox marketplace deployment (historical)
- Chromium Embedded Framework (historical)