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

ashhart/TensorFold

LLM Inference Engine for Metal, CUDA and Vulkan.

#LLM inference
Visit GitHub
Zig
2.4k
521
1 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

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

OfinTech Desk

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

Momentum

How fast ashhart/TensorFold 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 +2,316 in 61 days

0100200300
289

Forks +516 in 61 days

050100
96

Merged PRs 1,421 in 61 days

050100150
113

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

Top 25 in Python

10

Top 25 in Zig

1738355510954956711779949457332111156
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 PRsPythonZig
Mon, Sep 21, 2026+0+10Not trendingNot trending
Tue, Sep 22, 2026+0+00Not trendingNot trending
Wed, Sep 23, 2026+0+00Not trendingNot trending
Thu, Sep 24, 2026+0+00Not trendingNot trending
Fri, Sep 25, 2026+0+00Not trendingNot trending
Sat, Sep 26, 2026+157+109Not trendingNot trending
Sun, Sep 27, 2026+289+291#10Not trending
Mon, Sep 28, 2026+69+120Not trendingNot trending
Tue, Sep 29, 2026+82+110Not trendingNot trending
Wed, Sep 30, 2026+91+200Not trendingNot trending
Thu, Oct 1, 2026+104+280Not trendingNot trending
Fri, Oct 2, 2026+77+260Not trendingNot trending
Sat, Oct 3, 2026+52+140Not trendingNot trending
Sun, Oct 4, 2026+27+130Not trendingNot trending
Mon, Oct 5, 2026+35+92Not trendingNot trending
Tue, Oct 6, 2026+27+75Not trendingNot trending
Wed, Oct 7, 2026+38+53Not trendingNot trending
Thu, Oct 8, 2026+29+30Not trendingNot trending
Fri, Oct 9, 2026+40+109Not trendingNot trending
Sat, Oct 10, 2026+65+943Not trendingNot trending
Sun, Oct 11, 2026+36+87Not trendingNot trending
Mon, Oct 12, 2026+24+918Not trendingNot trending
Tue, Oct 13, 2026+29+430Not trendingNot trending
Wed, Oct 14, 2026+11+320Not trendingNot trending
Thu, Oct 15, 2026+7+60Not trending#17
Fri, Oct 16, 2026+20+667Not trending#3
Sat, Oct 17, 2026+13+30Not trending#8
Sun, Oct 18, 2026+18+366Not trending#3
Mon, Oct 19, 2026+19+30Not trending#5
Tue, Oct 20, 2026+19+40Not trending#5
Wed, Oct 21, 2026+19+30Not trending#5
Thu, Oct 22, 2026+10+41Not trending#10
Fri, Oct 23, 2026+10+70Not trending#9
Sat, Oct 24, 2026+11+20Not trending#5
Sun, Oct 25, 2026+15+80Not trending#4
Mon, Oct 26, 2026+8+70Not trending#9
Tue, Oct 27, 2026+13+20Not trending#5
Wed, Oct 28, 2026+17+614Not trending#6
Thu, Oct 29, 2026+17+231Not trending#7
Fri, Oct 30, 2026+10+433Not trending#11
Sat, Oct 31, 2026+18+345Not trending#7
Sun, Nov 1, 2026+20+438Not trending#7
Mon, Nov 2, 2026+17+564Not trending#9
Tue, Nov 3, 2026+16+666Not trending#9
Wed, Nov 4, 2026+31+459Not trending#4
Thu, Nov 5, 2026+9+370Not trending#9
Fri, Nov 6, 2026+23+556Not trending#4
Sat, Nov 7, 2026+11+486Not trending#5
Sun, Nov 8, 2026+9+560Not trending#7
Mon, Nov 9, 2026+14+462Not trending#3
Tue, Nov 10, 2026+16+125Not trending#3
Wed, Nov 11, 2026+62+740Not trending#2
Thu, Nov 12, 2026+132+620Not trending#1
Fri, Nov 13, 2026+151+1163Not trending#1
Sat, Nov 14, 2026+77+9632Not trending#1
Sun, Nov 15, 2026+101+2624Not trending#1
Mon, Nov 16, 2026+28+825Not trending#5
Tue, Nov 17, 2026+32+958Not trending#6
Wed, Nov 18, 2026+11+532Not trendingNot trending
Thu, Nov 19, 2026+18+3113Not trendingNot trending
Fri, Nov 20, 2026+12+024Not trendingNot trending
Total+2,316+5161,421
  • 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

    Nov 12 – Nov 14, 2026Best #7

    #1#5#10#15#20#25
    Top 10
    Oct 2026Nov
    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 ashhart/TensorFold, and every badge it has earned
    1. Nov 192 posts
      • Want to serve local LLMs without installing Python or MLX? TensorFold uses a Zig binary with Metal on Apple Silicon and CUDA on NVIDIA GPUs, then exposes OpenAI-compatible and Anthropic Messages…

        Read full on X, posted by @AKhomssi

        @AKhomssi · x.com

      • Tell your agent to update Tensorfold using the latest PRs for GLM-5.3-Flash that aren't on main yet.

        Read full on X, posted by @unigilby

        @unigilby · x.com

    2. Nov 171 post
      • Serve local language models — without setting up Python. TensorFold is a Zig-based language model inference engine for builders running models on Apple Silicon or NVIDIA GPUs. It helps you get a…

        Read full on X, posted by @DanKornas

        @DanKornas · x.com

    3. Nov 152 posts3 posts
      • So I wrote my own fixes as a Safari userscript. Now I can open projects, move between sessions, and every message has a heading. I'm coding in OpenCode with VoiceOver right now. My Taylor's Teardown…

        Read full on X, posted by @tayarndt

        @tayarndt · x.com

      • I dedicated some time to TensorFold. I will be sending more PR over there.

        Read full on X, posted by @AIFlow_ML

        @AIFlow_ML · x.com

      • 4/ ChromeDevTools/chrome-devtools-mcp 把 Chrome DevTools 交给编程 Agent 用的 MCP,方便 Agent 自己查页面、调前端。 今日 +664 ⭐ 5/ alibaba/open-code-review 阿里开源的混合架构代码审查:确定性流水线 + LLM Agent,行级评论,内置 NPE/线程安全/XSS/SQL 注入等规则。 今日…

        Read full on X, posted by @forgetsen

        @forgetsen · x.com

    4. Nov 142 posts
      • We see that it is fixed on the latest TensorFold release, we are working on updating. The update was not the problem, it just was a coincidence that triggered a bug in TensorFold, sorry

        Read full on X, posted by @iceoverflow

        @iceoverflow · x.com

      • TensorFold Runs LLMs Fast on Mac and NVIDIA GPUs One Zig binary serves LLMs on Apple Silicon and NVIDIA GPUs. #AI #OpenSource

        Read full on X, posted by @AnggaM39410

        @AnggaM39410 · x.com

    5. Nov 132 posts
      • TensorFold is worth a try if you want local Qwen on a Mac without Python: brew install, one serve command, an OpenAI- and Anthropic-compatible API. Zig binary, Metal + CUDA, Apache-2.0, 2k stars.…

        Read full on X, posted by @Muskmelon0706

        @Muskmelon0706 · x.com

      • four repos off github trending today that sit closer to the workshop than the usual agent hype. a small inference engine, two self-hostable agent setups and one for keeping coding agents honest.…

        Read full on X, posted by @aerthor0

        @aerthor0 · x.com

    You might also like

    Repositories close to ashhart/TensorFold
    FeaturedAdvertise to 180K+ monthly visitors
    Busbar

    Control what AI can do before it acts

    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

    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

    basecompute/baseRT

    Rust

    Fastest LLM inference runtime for Apple Silicon

    25021

    zolotukhin/zinc

    Zig

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

    53247

    waybarrios/vllm-mlx

    Python

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

    1.7k267

    SRSWTI/bodega-inference-engine

    Python

    fastest runtime for apple silicon.

    913

    Incept5-AI/inferd

    Python

    Native Apple Silicon inference engine for many AI agents at once: C++/Metal, agent-contexts API, 8-bit paged KV, SSD tier (Qwen3.8)

    373

    lithos-ai/lithos-metal

    Python

    lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.

    35132

    jundot/omlx

    Python

    LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

    23.8k2.4k

    recursive-oss/rec

    Python

    Our lightning-fast inference engine.

    28953

    SharpAI/SwiftLM

    Swift

    ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

    80263