Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Bifrost
Bifrost
Busbar
Busbar
OfinTech Desk
OfinTech Desk
It's a plan
It's a plan
Omnigraph
Omnigraph

Michael-A-Kuykendall/shimmy

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

#LLM inference
Visit GitHub
Rust
6k
618
5 contributors
Apache License 2.0
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Busbar

Control what AI can do before it acts

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Momentum

How fast Michael-A-Kuykendall/shimmy is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 21 – Nov 20, 2026

Stars +135 in 61 days

01020
16

Forks +20 in 61 days

0246
5

Merged PRs 0 in 61 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 21Sep 29Oct 7Oct 15Oct 23Oct 31Nov 8Nov 16
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Mon, Sep 21, 2026+4+00
Tue, Sep 22, 2026+2+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+1+10
Fri, Sep 25, 2026+4+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+10
Tue, Sep 29, 2026+4+00
Wed, Sep 30, 2026+4+10
Thu, Oct 1, 2026+2+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+2+00
Sun, Oct 4, 2026+2+10
Mon, Oct 5, 2026+12+50
Tue, Oct 6, 2026+5+00
Wed, Oct 7, 2026+16+00
Thu, Oct 8, 2026+3+20
Fri, Oct 9, 2026+4+10
Sat, Oct 10, 2026+7+20
Sun, Oct 11, 2026+3+00
Mon, Oct 12, 2026+1+00
Tue, Oct 13, 2026+6+00
Wed, Oct 14, 2026+4+00
Thu, Oct 15, 2026+1+10
Fri, Oct 16, 2026+2+00
Sat, Oct 17, 2026+2+00
Sun, Oct 18, 2026+1+00
Mon, Oct 19, 2026+3+10
Tue, Oct 20, 2026+2+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+00
Fri, Oct 23, 2026+0+00
Sat, Oct 24, 2026+2+00
Sun, Oct 25, 2026+1+00
Mon, Oct 26, 2026+3+00
Tue, Oct 27, 2026+2+00
Wed, Oct 28, 2026+1+00
Thu, Oct 29, 2026+3+00
Fri, Oct 30, 2026+1+00
Sat, Oct 31, 2026+2+00
Sun, Nov 1, 2026+1+00
Mon, Nov 2, 2026+3+10
Tue, Nov 3, 2026+0+00
Wed, Nov 4, 2026+3+00
Thu, Nov 5, 2026+0+00
Fri, Nov 6, 2026+1+00
Sat, Nov 7, 2026+1+00
Sun, Nov 8, 2026+1+00
Mon, Nov 9, 2026+2+00
Tue, Nov 10, 2026+0+00
Wed, Nov 11, 2026+0+00
Thu, Nov 12, 2026+0+30
Fri, Nov 13, 2026+0+00
Sat, Nov 14, 2026+0+00
Sun, Nov 15, 2026+2+00
Mon, Nov 16, 2026+3+00
Tue, Nov 17, 2026+0+00
Wed, Nov 18, 2026+0+00
Thu, Nov 19, 2026+6+00
Fri, Nov 20, 2026+0+00
Total+135+200
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1
  • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Rust

    Apr 27 – Jun 30, 2026#1 on 1 day

    #1#5#10#15#20#25
    Top 10
    May 2026Jun
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about Michael-A-Kuykendall/shimmy, and every badge it has earned
    1. Nov 61 post
      • 开机等 Ollama 醒的兄弟,换个 5MB 的单文件试试 Rust 写的 Shimmy,空载内存 50MB 上下,我第一跑差点以为没启动成功 直接抄: 1、GGUF 丢进目录 2、或让它自己去认 Hugging Face、Ollama 仓库我还在翻,你们谁先找到喊一声

        Read full on X, posted by @yang3izc

        @yang3izc · x.com

    2. 1 month earlier
    3. Oct 61 post
      • 本地跑大模型总觉得又重又笨?这个5MB的Rust替代品不妨一试,启动飞快、内存很小、API全兼容。 Shimmy单文件不到5MB,100毫秒内就能启动,内存占用仅50MB,OpenAI接口无缝对接——完全不像Ollama那样臃肿。 想轻量跑本地模型的,这个值得试试。 🔗

        Read full on X, posted by @x5cnhp

        @x5cnhp · x.com

    4. 11 days earlier
    5. Sep 251 post
      • Ollama 那些痛点,GitHub 新开源工具 Shimmy 直接冲着治。 单文件仅 5MB,本地推理又快又稳,自带完整 OpenAI 兼容 API,接入零成本。 Rust 打底:启动不到 100ms,内存约 50MB。 项目地址: 开箱即用:无需配置、自动分配端口,模型来源自动发现——Hugging Face、Ollama、本地目录都支持。 体积、启动、内存对比 Ollama…

        Read full on X, posted by @shenxiankk

        @shenxiankk · x.com

    6. 21 days earlier
    7. Sep 41 post
      • A local-inference project pulled out its own most proven code path on purpose, and the reasoning is worth a look. Shimmy is a single ~𝟱𝗠𝗕 Rust binary that serves an OpenAI-compatible API for local…

        Read full on X, posted by @lifeisameeme

        @lifeisameeme · x.com

    8. 14 days earlier
    9. Aug 211 post
      • 本地跑LLM最烦的就是装Python配llama.cpp,shimmy 5.8k星纯Rust写的WebGPU推理引擎,单个二进制文件GGUF模型直接跑,OpenAI API兼容。我在M2 Pro上试了7B量化模型,冷启动比Ollama快。坑是WebGPU在某些老GPU上支持不稳定。点开推文看项目地址

        Read full on X, posted by @senge0301

        @senge0301 · x.com

    10. 10 days earlier
    11. Aug 111 post
      • 本地跑大模型臃肿?试试这个Ollama5MB的Rust替代品,启动快、内存小、API全兼容。 Shimmy单文件不到5MB,100毫秒内就能跑起来,内存占用仅50MB,OpenAI接口无缝对接—完全不像Ollama那样笨重。 想轻量跑本地模型的,这个值得一试。 🔗

        Read full on X, posted by @bkdgiffug

        @bkdgiffug · x.com

    12. 2 months earlier
    13. Jun 81 post
      • 谁说本地跑大模型一定要臃肿?这个5MB的Rust小钢炮直接教Ollama做人。 Shimmy,单文件仅5MB,100毫秒内闪电启动,内存占用只有50MB,还100%兼容OpenAI API——Ollama拿什么跟你比? 嫌Ollama太笨重又想跑本地模型的,这波直接冲就完了。 🔗

        Read full on X, posted by @XAMTO_AI

        @XAMTO_AI · x.com

    14. 21 days earlier
    15. May 181 post
      • Ollama要凉了?这个5MB的小东西把它按地上摩擦 Rust写的Shimmy,单文件5MB,启动不到100ms,内存只吃50MB,还完美兼容OpenAI API——Ollama拿什么比? 想跑本地模型又嫌Ollama太臃肿的,这波直接冲。 🔗

        Read full on X, posted by @NFTCPS

        @NFTCPS · x.com

    You might also like

    Repositories close to Michael-A-Kuykendall/shimmy
    FeaturedAdvertise to 180K+ monthly visitors
    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    Busbar

    Control what AI can do before it acts

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    affifuddin-hazam/ghost-infer

    HTML

    Fast local LLM inference for the GPU you already have: one Rust binary, GGUF models, an OpenAI-compatible server and a chat page with a ghost.

    24216

    zolotukhin/zinc

    Zig

    Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

    53243

    zhongkaifu/TensorSharp

    C#

    A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability

    68176

    deepgrove-ai/llama.cpp

    C++
    288

    abetlen/llama-cpp-python

    Python

    Python bindings for llama.cpp

    10.7k1.4k

    Joakimpalm-Zen/xyntetik-runner

    C

    Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, byte-reproducibly. Tool calls survive the token limit; every run replays as a signed receipt. CPU/CUDA/Metal, OpenAI- and Anthropic-compatible.

    293

    antonellof/frink

    Rust

    Pure-Rust GGUF inference engine with quantized CPU, Metal & CUDA kernels, MoE support, OpenAI-compatible server. Benchmarked head-to-head against llama.cpp.

    7210

    machaao/llama-net

    Python

    Turn any Mac or GPU into an OpenAI-compatible inference node. One-command setup, automatic HTTPS, model management, and distributed request routing.

    27

    Nathanw1014/llama.cpp

    LLM inference in C/C++

    4315