mostlygeek/llama-swap
Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc
About the project
A Go proxy server that runs multiple local models and hot-swaps between them on demand, compatible with OpenAI and Anthropic APIs. Works with llama.cpp, vllm, stable-diffusion.cpp and other backends.
Useful for
- Serve multiple local LLMs behind one OpenAI-compatible endpoint with on-demand loading
- Free GPU memory by setting a ttl to auto-unload idle models
- Run a Docker container bundling llama.cpp, whisper.cpp and stable-diffusion.cpp behind one proxy
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 6 stars so far today, about 12 expected by the end of the day.
- Over the last two days the pace is 1.5× that of the previous week and a half.
- GitHub Trending Go today: #5, +18 stars.
- Recent forks include notable developers: @prabirshrestha (733 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 5,736
- Today
- 6 · ≈ 12 by evening
- Forks
- 479
- Issues and pull requests
- 1,065
- Watchers
- 24
- Language
- Go
- License
- MIT
- Latest release
- v257 · September 22, 2026
- Created
- October 4, 2024
- Last push
- September 23, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 23, 2026GitHub Trending Go today: #5, +18 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/mostlygeek/llama-swap)Similar by description
-
1.6
Edge0-AI/Edge0
An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run…
-
1.8
mmastrac/djev-spark
Container recipe for running DiffusionGemma 26B-A4B (NVFP4) on a DGX Spark with vLLM and a structured-decision server exposing Jev's /v1/systemone API.