Open source AI tools

A curated set of open source AI tools that run on your own server: model front-ends, recognition, video and audio processing, agents. Every entry is described in plain language.

Open source AI here means finished tools you deploy yourself: chat front-ends for local models, speech and text recognition, image, video and audio processing, search and agent systems. Your data stays on your own server, and usage of the model is not billed by a third-party service.

Only complete products get in, and only ones with a way to run them: Docker, a ready interface, a command line or an API. Developer libraries, link lists and bare model weights are left out, because you cannot launch them and get a result. Each card explains what the tool does, who it suits and what you will need to run it. The repository link is unlocked from the Creator plan (also on Make, N8N and Full).

FAQ

What do I need to run one of these?
Most often a server with Docker. Tools that work with video or large models need a GPU, and the description says so.
Does open source mean free?
The code is free. You still pay for the server, and sometimes for outside model access if the tool calls a cloud model.
Why self-host instead of using a cloud service?
Data never leaves your infrastructure, cost does not scale with request volume, and nobody can switch the tool off from outside. In exchange you take on updates and uptime.
Why are there no libraries or awesome lists?
You cannot get a working result out of them without writing software. This catalog collects things that run and pay off right after deployment.