colibri
colibri runs large open mixture-of-experts language models locally by streaming experts from disk, so the whole model need not fit in RAM. Use its dashboard or compatible APIs.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
colibri is a pure-C local inference engine for running large open mixture-of-experts language models on computers people already own. It keeps the resident model portion and an expert cache in RAM, while streaming other experts from disk, reducing the memory needed to use models too large to load at once. Setup checks the hardware, recommends a fitting model, and prepares the engine and model. Use the browser dashboard or connect apps through OpenAI- and Anthropic-compatible APIs.
Key features
- Checks hardware and recommends a model that fits available RAM and disk space.
- Streams experts from disk as needed instead of loading the whole model into RAM.
- Builds an engine locally when a compiler is available, or downloads a prebuilt engine.
- Downloads models with progress and resume, and provides a browser dashboard plus OpenAI- and Anthropic-compatible API endpoints.
Best for
People who want to run large open language models on a computer they already own, including systems without a GPU. The computer needs enough RAM and disk space for the selected model.
- Upstream
- JustVugg/colibri
- Fork on GitHub
- Guo-astro/colibri
- Upstream stars
- 42k
- Category
- AI agents and LLM tools
- Language
- C
- License
- Apache-2.0
- Forked
- 2026-10-12
- Sync status
- In syncLast synced 2026-10-19
More in AI agents and LLM tools
A collection of AI research skills and guides that helps researchers with idea evaluation, literature research, paper writing, and pre-submission review.
Forked 2026-10-18Last synced 2026-10-19Custom license (see repository)AI agents and LLM toolsGitHub
RLVE supports language model reinforcement learning with adaptive, verifiable environments for generating problems and evaluating model outputs.
Forked 2026-10-17Last synced 2026-10-19License: MITAI agents and LLM toolsGitHub
Provides modular Android development instructions for AI agents, helping them follow specialized workflows. Install individual skills or the full set with Android CLI.
Forked 2026-10-16Last synced 2026-10-19License: Apache-2.0AI agents and LLM toolsGitHub
Pi Agent is a local desktop app for using the Pi AI coding agent on macOS, Windows, and Linux. It helps you manage coding sessions, work with project files, and run saved prompts without setting up a terminal environment.
Forked 2026-10-15Last synced 2026-10-19License: MITAI agents and LLM toolsGitHub