SPspacebanana7·May 4, 2024
I believe it’s only compatible with full Chrome / Edge
https://github.com/abi/secret-llama?tab=readme-ov-file#syste...
In Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPUabi
secret-llama
TypeScript2024–2024
abi / secret-llama
secret-llama
Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.
3Distinct people
3Mentions
0Explicit recommenders
2.7KGitHub stars
What to know before exploring
What it is
Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.
GitHub
Where it is used
No documented product use has been verified yet.
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 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by hour3 dated mentions
Observed mentions: 2024-05-03 21:26:46 UTC to 2024-05-04 12:01:54 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| May 3, 21:00 | 2024-05-03 21:00:00 UTC | 2024-05-03 22:00:00 UTC | 1 | 1 | 0 |
| May 3, 22:00 | 2024-05-03 22:00:00 UTC | 2024-05-03 23:00:00 UTC | 0 | 0 | 0 |
| May 3, 23:00 | 2024-05-03 23:00:00 UTC | 2024-05-04 00:00:00 UTC | 1 | 0 | 1 |
| May 4, 00:00 | 2024-05-04 00:00:00 UTC | 2024-05-04 01:00:00 UTC | 0 | 0 | 0 |
| May 4, 01:00 | 2024-05-04 01:00:00 UTC | 2024-05-04 02:00:00 UTC | 0 | 0 | 0 |
| May 4, 02:00 | 2024-05-04 02:00:00 UTC | 2024-05-04 03:00:00 UTC | 0 | 0 | 0 |
| May 4, 03:00 | 2024-05-04 03:00:00 UTC | 2024-05-04 04:00:00 UTC | 0 | 0 | 0 |
| May 4, 04:00 | 2024-05-04 04:00:00 UTC | 2024-05-04 05:00:00 UTC | 0 | 0 | 0 |
| May 4, 05:00 | 2024-05-04 05:00:00 UTC | 2024-05-04 06:00:00 UTC | 0 | 0 | 0 |
| May 4, 06:00 | 2024-05-04 06:00:00 UTC | 2024-05-04 07:00:00 UTC | 0 | 0 | 0 |
| May 4, 07:00 | 2024-05-04 07:00:00 UTC | 2024-05-04 08:00:00 UTC | 0 | 0 | 0 |
| May 4, 08:00 | 2024-05-04 08:00:00 UTC | 2024-05-04 09:00:00 UTC | 0 | 0 | 0 |
| May 4, 09:00 | 2024-05-04 09:00:00 UTC | 2024-05-04 10:00:00 UTC | 0 | 0 | 0 |
| May 4, 10:00 | 2024-05-04 10:00:00 UTC | 2024-05-04 11:00:00 UTC | 0 | 0 | 0 |
| May 4, 11:00 | 2024-05-04 11:00:00 UTC | 2024-05-04 12:00:00 UTC | 0 | 0 | 0 |
| May 4, 12:00 | 2024-05-04 12:00:00 UTC | 2024-05-04 13:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
3 sourcesModels sizes are listed here https://github.com/abi/secret-llama but yeah, > 4GB for the Llama 3 model.
In Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPUShow HN: I built a free in-browser Llama 3 chatbot powered by WebGPU
I spent the last few days building out a nicer ChatGPT-like interface to use Mistral 7B and Llama 3 fully within a browser (no deps and installs).
I’ve used the WebLLM project by MLC AI for a while to interact with LLMs in the browser when handling sensitive data but I found their UI quite lacking for serious use so I built a much better interface around WebLLM.
I’ve been using it as a therapist and coach. And it’s wonderful knowing that my personal information never leaves my local computer.
Should work on Desktop with Chrome or Edge. Other browsers are adding WebGPU support as well - see the Github for details on how you can get it to work on other browsers.
Note: after you send the first message, the model will be downloaded to your browser cache. That can take a while depending on the model and your internet connection. But on subsequ
Read the rest
ent page loads, the model should be loaded from the IndexedDB cache so it should be much faster.
The project is open source (Apache 2.0) on Github. If you like it, I’d love contributions, particularly around making the first load faster.
Github: https://github.com/abi/secret-llama
Demo: https://secretllama.com