tabby

I only use copilot for the occasional auto-complete suggestion. I'm betting I could run a lightweight local LLM with llama.cpp to get similar functionality. Maybe this would be a decent replacement https://github.com/TabbyML/tabby

People in government agencies, defence and aerospace companies write code in airgapped environments every day. Essentials like version control, CI/CD and artifact repositories are readily available, as they always have been. Gitlab, Artifactory etc all run just fine. The problem you'll face with LLM assistants is they require very substantial hardware. I don't know how well that's going to fit your laptop-in-the-middle-of-nowhere use case, but there are projects floating around. https://github.com/TabbyML/tabby

Mistral (an LLM company) is not really a substitute for cursor (an IDE). Tabby is probably the closest open-source alternative. https://github.com/TabbyML/tabby

You have it wrong. Neither "open source" nor "free software" imply free-of-cost. Paid software with open and free license is very much a thing. If you want to drill into the details of the licenses: https://github.com/TabbyML/tabby/blob/main/LICENSE

Very cool. I'm especially happy to see that there is an Eclipse client[1]. One note though: I had to dig around a bit to find the info about the Eclipse client. It's not mentioned in the main readme, or in the list of IDE extensions in the docs. Not sure if that's an oversight or because it's not "ready for prime time" yet or what. [1]: https://github.com/TabbyML/tabby/tree/3bd73a8c59a1c21312e812...

Yes - AMD GPU is supported through vulkan backend: https://github.com/TabbyML/tabby/releases/tag/v0.23.0 https://tabby.tabbyml.com/blog/2024/05/01/vulkan-support/

Not yet, consider subscribe https://github.com/TabbyML/tabby/issues/322 for future updates!

As someone unfamiliar with local AIs and eager to try, how does the “run tabby in 1 minute”[1] compare to e.g. chatgpt’s free 4o-mini? Can I run that docker command on a medium specced macbook pro and have an AI that is comparably fast and capable? Or are we not there (yet)? Edit: looks like there is a separate page with instructions for macbooks[2] that has more context. > The compute power of M1/M2 is limited and is likely to be sufficient only for individual usage. If you require a shared instance for a team, we recommend considering Docker hosting with CUDA or ROCm. [1]: https://github.com/TabbyML/tabby#run-tabby-in-1-minute docker run -it --gpus all -p 8080:8080 -v $HOME/.tabby:/data tabbyml/tabby serve --model StarCoder-1B --device cuda --chat-model Qwen2-1.5B-Instruct [2]: https://tabby.tabbyml.com/docs/quick-start/installatio

A couple of other ones https://github.com/TabbyML/tabby https://github.com/fauxpilot/fauxpilot

https://github.com/TabbyML/tabby can run self-hosted AI coding assistants. I tried it a while ago and it worked with Nvim pretty easily. There is a VS code extension too. The extension will just sort of "read" with you and provide suggestions from time to time. Anytime the suggestion is good you can press some key (<TAB> by default) to accept it. It's basically autocomplete on steroids.

Checkout tabby: https://github.com/TabbyML/tabby Blog post on repository context: https://tabby.tabbyml.com/blog/2023/10/16/repository-context... (Disclaimer: I started this project)

NixOS just got tabbyml[1] which is built on llama-cpp. Working on systemsd services the weekend and updating latest tabbyml release which supports rocm in addition to cuda [1] https://github.com/TabbyML/tabby [2] https://github.com/NixOS/nixpkgs/pull/291744

Nice implementation! It should serve as a great reference for a minimal Tabby's backend API. Thank you for sharing it! Yeah - ultimately, it won't be as performant or feature-rich compared to https://github.com/TabbyML/tabby, but it's still perfect for educational purposes!