shimmy is an open-source LLM inference tool written in Rust, released under the Apache-2.0 license. It has 6k GitHub stars and 586 forks, and was last updated in October 2026. Topics include api-server, command-line-tool and developer-tools.
“⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.”
— Michael-A-Kuykendall, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 5,983 |
| Forks | 586 |
| Language | Rust |
| License | Apache-2.0 |
| Last updated | |
| Owner | Michael-A-Kuykendall |
| Repository | Michael-A-Kuykendall/shimmy |
Tags
api-servercommand-line-tooldeveloper-toolsggufhuggingfacehuggingface-modelshuggingface-transformersinference-server
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.