HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
karpathy
nanochat
Python2025–2026
karpathy / nanochat

nanochat

The best ChatGPT that $100 can buy.

24Distinct people
24Mentions
0Explicit recommenders
60.5KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

The best ChatGPT that $100 can buy.

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 3:44:08 PM UTC.

Mentions over time

HN mentions by month24 dated mentions

Observed mentions: 2025-10-13 15:22:47 UTC to 2026-08-24 10:00:22 UTC.

024682025-10-01 00:00:00 UTC to 2025-11-01 00:00:00 UTC (exclusive): 8 mentions; 2 submissions, 6 commentsOct 20252025-11-01 00:00:00 UTC to 2025-12-01 00:00:00 UTC (exclusive): 5 mentions; 1 submissions, 4 comments2025-12-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-01-01 00:00:00 UTC to 2026-02-01 00:00:00 UTC (exclusive): 5 mentions; 2 submissions, 3 comments2026-02-01 00:00:00 UTC to 2026-03-01 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-03-01 00:00:00 UTC to 2026-04-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMar 20262026-04-01 00:00:00 UTC to 2026-05-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-05-01 00:00:00 UTC to 2026-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-01 00:00:00 UTC to 2026-07-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-07-01 00:00:00 UTC to 2026-08-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-08-01 00:00:00 UTC to 2026-09-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsAug 2026

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Oct 20252025-10-01 00:00:00 UTC2025-11-01 00:00:00 UTC826
Nov 20252025-11-01 00:00:00 UTC2025-12-01 00:00:00 UTC514
Dec 20252025-12-01 00:00:00 UTC2026-01-01 00:00:00 UTC202
Jan 20262026-01-01 00:00:00 UTC2026-02-01 00:00:00 UTC523
Feb 20262026-02-01 00:00:00 UTC2026-03-01 00:00:00 UTC110
Mar 20262026-03-01 00:00:00 UTC2026-04-01 00:00:00 UTC101
Apr 20262026-04-01 00:00:00 UTC2026-05-01 00:00:00 UTC101
May 20262026-05-01 00:00:00 UTC2026-06-01 00:00:00 UTC000
Jun 20262026-06-01 00:00:00 UTC2026-07-01 00:00:00 UTC000
Jul 20262026-07-01 00:00:00 UTC2026-08-01 00:00:00 UTC000
Aug 20262026-08-01 00:00:00 UTC2026-09-01 00:00:00 UTC101

What Hacker News says

8 sources
I didn't say that there aren't people doing cutting edge stuff. But even John Romero did the boring stuff along with the cool stuff. Andrej Karpathy wrote a ton of boilerplate Python to get his stuff up and running[0]. Or are you claiming that every single line of the nanochat[0] project is peak computer science algorithms no LLM can replicate today? Take the initial commit tasks/ directory for example[1]. Dude is easily in the top 5 AI scientists in the world and he still spends a good time writing pretty basic string wrangling in Python. My basic point here is that LLMs automate generating the boilerplate to a crazy degree, letting us spend more time in the bits that aren't boring and are actually challenging and interesting. [0] https://github.com/karpathy/nanochat [1] https://github.com/karpathy/nanochat/tree/master/tasks
In Why the push for Agentic when models can barely follow a simple instruction?
Leading AI researcher Andrej Karpathy created a NanoLLM using available training data and $100 worth of (high-end) rented Cloud computer time. The original post is https://github.com/karpathy/nanochat/discussions/1 The post this is on is commentary from simonw about Karpathy's post. The NanoLLM he created is, um, not very good. So you wouldn't want to use it for anything other than learning and entertainment. But it's really small, which means it runs on small underpowered computers. There's a web-gui, so you interact with it just like ChatGPT on your little computer. Also for learning purposes, Karpathy shared the code he used to create NanoLLM, so you can run it at home and create your own model and chat with it. Given that GPT-5 reportedly cost $100 million to train, being able to create one, even a terrible one, for $100, shows how th
Read the rest
e field keeps marching on.
In Nanochat

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.