Questions? Answered.
Everything you need to know before installing.
Is Alice free?+
Yes. Alice is open source under the MIT license and free to use, modify, and self-host.
Does it run locally?+
The agent core runs on your machine. You choose which model provider to connect; your data never has to leave your system unless you configure external APIs.
Do I need to know how to code?+
A little. Alice is built for developers and technical makers who want a programmable assistant.
Can I add my own skills?+
Absolutely. Skills are plain code and configuration files. Add integrations, cron jobs, memory sources, or custom tools.
Which models are supported?+
Any model reachable via API: OpenAI, Anthropic, local Ollama / llama.cpp, OpenRouter, and more through the gateway.
How is this different from other agents?+
Alice is local-first, memory-persistent, and designed to be extended by you, not locked behind a SaaS subscription.
Does it work offline or with local models?+
Yes. Alice runs with Ollama, llama.cpp, vLLM, or any OpenAI-compatible server. No cloud, no API keys.
Is my data sent anywhere?+
Only if you use a remote provider (OpenRouter, OpenAI, Anthropic...). With local models nothing leaves your machine. Sessions and memory live in ~/.alice/.
How much does Alice cost?+
Alice is free and open source (MIT). You only pay for the model usage you choose — or nothing with local models.
Can I use it in my own Python project?+
Yes. Alice works as a library: import the agent and run prompts programmatically from your code.
What's the difference between memory and skills?+
Memory stores facts across sessions (who you are, your preferences). Skills are procedure documents the agent creates or installs to repeat workflows.
Can multiple people or profiles use it?+
Each profile has its own memory, sessions, and skills. You can run several isolated agents on the same machine — even on the same repo with git worktrees.