# mostlygeek/llama-swap

> 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.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 5,736 total · +6 stars today, ≈ 11 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Go · License: MIT · Created: 2024-10-04 · Last push: 2026-09-23
- GitHub: https://github.com/mostlygeek/llama-swap · Page: https://gitnova.dev/en/r/mostlygeek/llama-swap

## 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

## Why it’s here

- 6 stars so far today, about 11 expected by the end of the day.
- GitHub Trending Go today: #5, +18 stars.
- Recent forks include notable developers: @prabirshrestha (733 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 479
- Issues and pull requests: 1,065
- Watchers: 24
- Average over the last week: 10 per day
- Usual pace: 9 per day
- Stars in the last hour (measured): 0
- Latest release: v257 (2026-09-22)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-25 … 2026-09-23: 7, 10, 8, 11, 13, 11, 12, 13, 14, 5, 8, 8, 9, 21, 9, 9, 7, 8, 11, 5, 11, 2, 13, 10, 6, 7, 14, 6, 14, 6

## Spotted in now

- GitHub Trending Go today: #5, +18 stars

## Similar by description

1. **Edge0-AI/Edge0** — 1.6 · Cooling · Language models · Python · +4 stars today, ≈ 8 by evening
   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 model tiers (35B and…
   Full card: https://gitnova.dev/en/r/Edge0-AI/Edge0.md
2. **mmastrac/djev-spark** — 1.9 · Cooling · Language models · HTML · +6 stars today, ≈ 10 by evening
   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.
   Full card: https://gitnova.dev/en/r/mmastrac/djev-spark.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-23 13:41 UTC, updated every 30 minutes.