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

karpathy/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

#LLM training
Visit GitHub
Python
64.9k
11.2k
37 contributors
MIT License
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

Omnigraph

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

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 karpathy/nanoGPT 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 20 – Nov 19, 2026

Stars +1,680 in 61 days

050100
65

Forks +415 in 61 days

01020
17

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 20Sep 28Oct 6Oct 14Oct 22Oct 30Nov 7Nov 15
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
Sun, Sep 20, 2026+28+50
Mon, Sep 21, 2026+37+70
Tue, Sep 22, 2026+26+40
Wed, Sep 23, 2026+20+50
Thu, Sep 24, 2026+17+50
Fri, Sep 25, 2026+12+60
Sat, Sep 26, 2026+21+80
Sun, Sep 27, 2026+17+30
Mon, Sep 28, 2026+19+80
Tue, Sep 29, 2026+24+80
Wed, Sep 30, 2026+19+40
Thu, Oct 1, 2026+13+40
Fri, Oct 2, 2026+26+30
Sat, Oct 3, 2026+12+70
Sun, Oct 4, 2026+26+10
Mon, Oct 5, 2026+21+60
Tue, Oct 6, 2026+15+10
Wed, Oct 7, 2026+25+30
Thu, Oct 8, 2026+31+70
Fri, Oct 9, 2026+31+80
Sat, Oct 10, 2026+27+30
Sun, Oct 11, 2026+15+70
Mon, Oct 12, 2026+34+40
Tue, Oct 13, 2026+35+70
Wed, Oct 14, 2026+27+100
Thu, Oct 15, 2026+27+60
Fri, Oct 16, 2026+23+40
Sat, Oct 17, 2026+30+40
Sun, Oct 18, 2026+18+100
Mon, Oct 19, 2026+26+50
Tue, Oct 20, 2026+22+50
Wed, Oct 21, 2026+26+70
Thu, Oct 22, 2026+32+90
Fri, Oct 23, 2026+24+60
Sat, Oct 24, 2026+20+60
Sun, Oct 25, 2026+21+40
Mon, Oct 26, 2026+19+50
Tue, Oct 27, 2026+58+130
Wed, Oct 28, 2026+37+90
Thu, Oct 29, 2026+26+80
Fri, Oct 30, 2026+34+110
Sat, Oct 31, 2026+36+90
Sun, Nov 1, 2026+51+170
Mon, Nov 2, 2026+55+100
Tue, Nov 3, 2026+38+100
Wed, Nov 4, 2026+30+50
Thu, Nov 5, 2026+26+70
Fri, Nov 6, 2026+23+90
Sat, Nov 7, 2026+26+80
Sun, Nov 8, 2026+16+50
Mon, Nov 9, 2026+26+80
Tue, Nov 10, 2026+30+100
Wed, Nov 11, 2026+22+70
Thu, Nov 12, 2026+65+170
Fri, Nov 13, 2026+34+50
Sat, Nov 14, 2026+26+70
Sun, Nov 15, 2026+38+50
Mon, Nov 16, 2026+36+130
Tue, Nov 17, 2026+37+60
Wed, Nov 18, 2026+27+100
Thu, Nov 19, 2026+17+10
Total+1,680+4150
  • 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

    Oct 12, 2023 – Dec 13, 2025Best #2

    #1#5#10#15#20#25
    Top 10
    Oct 2023AprOctAprOctApr
    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 karpathy/nanoGPT, and every badge it has earned
    1. Nov 131 post
      • 炸裂!!OpenAI 的联合创始人 Karpathy 在Github 开源了6个项目,总计超30万颗星! 这位创始人把从训练 GPT、到让模型自己做研究的一整套材料,都开源在了 GitHub 上⬇️: 1. autoresearch · 近 10 万星 能自己连夜跑实验,只把有用的结果留下 2. nanoGPT · 6.5 万星 从零开始训练一个自己的 GPT,很多人入门都是看这个仓库 3.…

        Read full on X, posted by @HeLi8866

        @HeLi8866 · x.com

    2. Nov 122 posts
      • 3 GitHub repos worth reading for the code, not just using: 1. nanoGPT: Understand how GPT works from scratch, including attention, transformer blocks, and token generation. 2. tinygrad:…

        Read full on X, posted by @cneuralnetwork

        @cneuralnetwork · x.com

      • 🤯卧槽,Karpathy 把自己整套 AI 课,免费开源到 GitHub 了!?! 按学习顺序,一共 7 个仓库: → nn-zero-to-hero,从零开始搭神经网络的视频课 → micrograd,用很少的代码把 AI 怎么学会的那套数学讲清楚 → makemore,一个会自己编新名字的小模型 → minbpe,讲模型怎样把句子切成 token → nanoGPT,可以自己动手训练一个…

        Read full on X, posted by @HeLi8866

        @HeLi8866 · x.com

    3. Nov 91 post
      • 还有一些类似的小项目,一些最小化机器学习/深度学习相关的研究实现,可以快速学习到这个领域的知识原理: - minimalRL:minimalRL 是一个用 PyTorch 实现的极简强化学习(RL)算法集合 - micrograd:纯教学工具,大约 100 行代码实现标量自动微分(autograd),再加约 50 行做一个迷你神经网络库。 - nanoGPT:GPT 训练的实际工作原理 -…

        Read full on X, posted by @alacheng

        @alacheng · x.com

    4. Nov 71 post
      • some minimal ML implementations that are genuinely worth studying: - micrograd: autograd and backpropagation from scratch - nanoGPT: how GPT training actually works - minGPT: transformers without…

        Read full on X, posted by @cneuralnetwork

        @cneuralnetwork · x.com

    5. Nov 31 post
      • GitHub 上免费放了一整套 AI 学位课程。 7 个仓库,306,741 星标,按正确顺序学下来,能从反向传播一路走到能通宵跑研究的智能体。 每个仓库都是前一个的下一层。仓库地址👇

        Read full on X, posted by @wanerfu

        @wanerfu · x.com

    6. Nov 22 posts
      • 花几千块报AI课之前,先把这10个免费仓库啃一遍。 我给自己排了一条12周的路线,每个仓库只干一件事:跑通,再改一点。 1. generative-ai-for-beginners(122.8k⭐) 微软出的21节课,提示词、RAG、Agent从零讲起 我的看法:第一周就从这开始,别跳 2. agents-course(34.3k⭐) Hugging Face官方Agent课,做完能拿证书…

        Read full on X, posted by @waveking1314

        @waveking1314 · x.com

      • 当世最强的AI大神Karpathy 在 GitHub 上留下的这 7 个仓库,可以说是全网含金量最高的免费 AI 学位了, 没有昂贵门票,没有商业营销,7 个精心打磨的GitHub代码仓库,是他留给这个时代最宝贵也最纯粹质朴的一份礼物! 看遍整个开源社区,能把大模型底层逻辑拆解得如此优雅纯粹的,大概只有 Andrej Karpathy 一人了,…

        Read full on X, posted by @AYi_AInotes

        @AYi_AInotes · x.com

    7. Nov 12 posts
      • 📎 原文出处(下)+ 那个 2 小时免费讲座 ⑦ Karpathy:Agents → Harness → Loops → Graphs 他说「世界有资格搞懂宇宙怎么运作」,然后顺手把整门课放出来了

        Read full on X, posted by @reamory_eth

        @reamory_eth · x.com

      • 哇靠!Karpathy 的 GitHub 仓库,简直是一所免费的 AI 大学!🤯 7 个开源项目,累计超过 30 万 Star! 从神经网络、反向传播,到大模型训练,再到能自主完成任务的 AI Agent。 按照顺序学下来,相当于走完一套完整的 AI 技术进阶路线。 想系统学习 AI 的朋友,这波真的值得收藏! 7 个 GitHub 仓库地址放下面👇

        Read full on X, posted by @AndyL5cc

        @AndyL5cc · x.com

    You might also like

    Repositories close to karpathy/nanoGPT
    FeaturedAdvertise to 180K+ monthly visitors
    Omnigraph

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

    OfinTech Desk

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

    Bifrost

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

    It's a plan

    Open-source Linear alternative

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

    Busbar

    Control what AI can do before it acts

    karpathy/build-nanogpt

    Python

    Video+code lecture on building nanoGPT from scratch

    5.7k898

    karpathy/minGPT

    Python

    A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

    25k3.3k

    ystemsrx/mini-nanoGPT

    Python

    One-click training of your own GPT. Training a GPT has never been easier for beginners. / 一键预训练+SFT一个属于自己的LLM,0基础训练GPT原来可以这么简单?

    38754

    younissk/nanoBeard

    Python

    The code I used to train all nanoBeard models

    10714

    openai/gpt-2

    Python

    Code for the paper "Language Models are Unsupervised Multitask Learners"

    25k5.4k

    KellerJordan/modded-nanogpt

    Python

    NanoGPT (124M) in 90 seconds

    6.1k896

    prabeakarve/microgpt

    Python

    A from-scratch, dependency-free GPT implementation in pure NumPy: byte-level tokenizer, multi-head self-attention, Adam trainer, and top-k sampler.

    51

    jaymody/picoGPT

    Python

    An unnecessarily tiny implementation of GPT-2 in NumPy.

    3.5k466

    karpathy/nanochat

    Python

    The best ChatGPT that $100 can buy.

    60.7k8.8k