I built local copilot alternative using Codellama
Hey, HN! I was trying to find a good Copilot alternative since my experience with copilot degraded a lot and recent OpenAI drama leaves me no hope for improvement and i decided to take a look at self-hosting options. At the same time Copilot net is a small one - just 12b parameters and 2k of context. You can run much bigger networks locally in 2023. I have figured out that there are no good local options: most of the VS Code plugins simply connect neural networks to the code while copilot has extensive post and pre processing steps. Some of them still work with original copilot plugin (ie…
In plain words
This is a locally-hosted code completion tool built with Codellama that runs as a Visual Studio Code extension. It allows developers to run larger language models on their own machines instead of relying on cloud-based alternatives. The tool includes preprocessing and postprocessing steps similar to GitHub Copilot, enabling more accurate code suggestions without sending data to external servers. It's designed for programmers seeking privacy-respecting, self-hosted code assistance.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey, HN! I was trying to find a good Copilot alternative since my experience with copilot degraded a lot and recent OpenAI drama leaves me no hope for improvement and i decided to take a look at self-hosting options. At the same time Copilot net is a small one - just 12b parameters and 2k of context. You can run much bigger networks locally in 2023. I have figured out that there are no good local options: most of the VS Code plugins simply connect neural networks to the code while copilot has extensive post and pre processing steps. Some of them still work with original copilot plugin (ie sends data to MS), some require complicated setup to make it work. I implemented very basic ones to check if this would work and in my experience it works really good and i wanted to share it on HN. Feedback is appreciated! Sources are here: https://github.com/ex3ndr/llama-coder
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, November 2023
the whole month →
Discover & book top creators to promote your product
Growth · 2023 · passionfroot.me
