Documentation

Suzent is a sovereign AI agent: an open-source, local-first agent whose identity, memory, skills, workspace, and runtime stay under your control, independent of any model or platform. For the definition of agent sovereignty and the five-question ownership test, see what makes an agent sovereign.

Getting Started

• What is Suzent?: what a sovereign agent is and what Suzent can do
• Quickstart: install, connect a model, and start chatting
• Desktop, phone, and browser: every way to reach your agent
• Updating: update Suzent and upgrade an existing install

Using Suzent

• Working with your agent, Organizing work into projects, Making it yours

Features

• Overview
• Memory, Notebook, Advanced memory settings
• Tools, Permissions & approvals, Browser
• Skills, Workspace & sandbox, Automation
• Devices & other agents, GitHub Sync

Models

• Models & Providers and Model roles
• Cloud: OpenAI, ChatGPT Subscription, Anthropic, Google Gemini, xAI, DeepSeek, DashScope, Moonshot, Zhipu AI, MiniMax, Xiaomi MiMo, OpenRouter
• Local and self-hosted: Ollama, vLLM, SGLang, LiteLLM Proxy

Chat apps

• Overview and Access control & pairing
• Telegram, Slack, Discord, Feishu (Lark), WeChat

Tutorials

• Run everything on your own computer
• Get a morning briefing on Telegram
• Work on a folder safely

Reference

• Command line, Slash commands, Settings pages, Configuration files, FAQ & troubleshooting

Development

For contributors working on Suzent's own code. You don't need any of this to use Suzent. Pages here describe what exists today; planned work lives in the Roadmap.

Contributing: Development guide, Web UI, Docker services, Releasing, Mobile releases, Updating model capabilities

Architecture: Tool system, Canvas (A2UI), Agent communication, System reminders, Post-processing, Stream recovery, Memory architecture, Memory internals, Model capabilities, Native mobile

Protocols & APIs: HTTP API, Node protocol, Node security, A2A, ACP