Loading this page…
AI Personal Assistants
Chat with AI on your computer, including offline models.
Jan Desktop is free under Apache-2.0. Local inference has no per-message software fee; hardware, electricity and model licenses still apply. Connected cloud providers have their own API prices.
Check official pricing
Run AI models locally or connect to cloud, privately. A self-hosting option is recorded for this project. Review the official deployment instructions and maintenance requirements before running it yourself.
Technologies recorded in the catalog snapshot.
Connect an AI assistant to the tools and conversations where you already work.
The MIT-licensed assistant software is free to run on your own machine. Cloud models, connected services and hosted machines can require payment; subscriptions or API keys are supplied separately.
Use a desktop AI agent with persistent context and integrations across communication platforms.
The MIT-licensed agent can run locally without a software license fee. Model APIs, optional Nous Portal subscriptions, search or other services, and cloud machines may charge separately. A free agent is not free access to every model.
Download and run AI models on your own computer.
Local models are free to run on your own hardware. Cloud Free includes limited starter usage; Pro is USD 20/month and Max USD 100/month. Usage credits and model token rates apply, and paid allowances do not roll over.
Chat with AI models in your own browser-based workspace.
Use the self-hosted UI with its required branding under the current license. There is no included paid-model allowance: cloud APIs, servers and storage can cost extra. Removing branding or qualifying enterprise uses may require a separate license; do not assume the current release is unrestricted BSD.
Run language model inference across different hardware with a portable C and C++ engine.
The MIT-licensed inference runtime has no software license fee. Supply suitable hardware and check each model license. Rented GPU or server resources and unrelated hosted services can cost extra.
Serve language models through an inference engine designed for throughput and efficient resource use.
The Apache-2.0 serving software is free. Models, GPU hardware, electricity, storage and cloud compute have separate terms and costs. Installing the runtime does not include a hosted inference allowance.
