[ INDEX : FAQ ]
What is PraisonAI?
PraisonAI helps banks, insurers and hospitals run AI agents on their own computers, even fully offline, so their private data never leaves the building. It is built on our open-source Python agent framework, which is live today. See the Platform page for an overview.
Does it run fully offline?
Yes. Agents can run on your own computers with your own models, such as Llama, Qwen and Gemma through Ollama or vLLM. They keep working with no internet connection. See local models and offline install.
What is in early access?
The open-source framework is live today. The handover is in early access: each task moves to your own AI only after it passes a test. If quality slips, it moves back automatically, and every step is recorded for regulators. We’re inviting our first design partners. Talk to us.
Can I self-host?
Yes. The framework is MIT licensed and runs on your own computers. See Enterprise for how regulated teams run it.
Does it support MCP?
Yes. PraisonAI has native Model Context Protocol support. See MCP documentation.
Which models are supported?
OpenAI, Anthropic, Gemini, Groq and many more via LiteLLM, plus your own local models through Ollama or vLLM. See documentation for the full list.
Can enterprises use it?
Yes. Banks, insurers and hospitals can run agents on their own computers with their own models, so private data stays inside the building. See Enterprise.
Can agencies partner with PraisonAI?
Yes. Consultancies and implementation firms can join the Partner Programme.
Is it open source?
The framework is. It is MIT licensed, and the source code is at GitHub. The early-access handover is a separate product, and that licence does not cover it.
How do I get started?
Install via pip and follow the quickstart at praison.ai/docs, or read the Platform overview first.
Still Have Questions?
Reach out to the team or explore the documentation.