Ollama
Runs open AI models on your own computer and gives other apps a local server to use them.
Instead of Hosted chatbots such as ChatGPT
Screenshot from ollama.com, taken 2026-10-23, shown to help you recognise the tool. It belongs to its maker. Ask us to remove it.
Ollama is an MIT-licensed tool that runs open AI models on your own machine and exposes them through a local server, so other apps can use them. Installers exist for Mac, Windows and Linux, with an official Docker image, and its page says you can also run models in the cloud, which sends your prompts off your computer. We could not confirm its pricing or whether the cloud options need an account.
It is the piece that makes a private, local assistant possible: your prompts stay on your computer when you use local models, and you can swap models whenever you like. The better models need a capable computer, and the company behind it decides how its cloud options develop.
- Runs open AI models on your own machine behind a local server
- MIT licensed, with installers for Mac, Windows and Linux
- Cloud models are optional and send your prompts off your computer
What stands out
Do you make Ollama? Get the badge for your site
This badge reports a dated review. It is not a certification and it costs nothing. Link it to this page and leave the numbers alone: the image always shows the current score.
For dark backgrounds, use ollama-dark.svg in place of ollama-light.svg.
For comparison, we also reviewed ChatGPT (14/30) and Claude (15/30) as a benchmark.
Other tools for “get an ai helper i control”
- JanAn open-source chat app that runs AI models fully offline on your computer.
gooseAn open-source AI agent that runs on your machine and works with the model you choose.
OpenClawAn open-source AI assistant that runs on your own computer and works through your chat apps.
Hermes AgentAn open-source AI agent that learns skills from the tasks it does and remembers you.