HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
jawerty
10x-React-Engineer
Jupyter Notebook2023–2023
jawerty / 10x-React-Engineer

10x-React-Engineer

With just Llama-2, generate full React codebases from a single prompt

Web Development
Explore on GitHubRead Hacker News discussions
2Distinct people
5Mentions
0Explicit recommenders
103GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

With just Llama-2, generate full React codebases from a single prompt

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, 3:56:07 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 6-hour interval5 dated mentions

Observed mentions: 2023-08-15 13:01:55 UTC to 2023-08-22 14:54:56 UTC.

012023-08-15 12:00:00 UTC to 2023-08-15 18:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsAug 15, 12:002023-08-15 18:00:00 UTC to 2023-08-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-16 00:00:00 UTC to 2023-08-16 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-16 06:00:00 UTC to 2023-08-16 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-16 12:00:00 UTC to 2023-08-16 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-16 18:00:00 UTC to 2023-08-17 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2023-08-17 00:00:00 UTC to 2023-08-17 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-17 06:00:00 UTC to 2023-08-17 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-17 12:00:00 UTC to 2023-08-17 18:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2023-08-17 18:00:00 UTC to 2023-08-18 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-08-18 00:00:00 UTC to 2023-08-18 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-18 06:00:00 UTC to 2023-08-18 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-18 12:00:00 UTC to 2023-08-18 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-18 18:00:00 UTC to 2023-08-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-19 00:00:00 UTC to 2023-08-19 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsAug 19, 00:002023-08-19 06:00:00 UTC to 2023-08-19 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-19 12:00:00 UTC to 2023-08-19 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-19 18:00:00 UTC to 2023-08-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-20 00:00:00 UTC to 2023-08-20 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-20 06:00:00 UTC to 2023-08-20 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-20 12:00:00 UTC to 2023-08-20 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-20 18:00:00 UTC to 2023-08-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-21 00:00:00 UTC to 2023-08-21 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-21 06:00:00 UTC to 2023-08-21 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-21 12:00:00 UTC to 2023-08-21 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-21 18:00:00 UTC to 2023-08-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-22 00:00:00 UTC to 2023-08-22 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-22 06:00:00 UTC to 2023-08-22 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-08-22 12:00:00 UTC to 2023-08-22 18:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsAug 22, 12:00

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
Aug 15, 12:002023-08-15 12:00:00 UTC2023-08-15 18:00:00 UTC110
Aug 15, 18:002023-08-15 18:00:00 UTC2023-08-16 00:00:00 UTC000
Aug 16, 00:002023-08-16 00:00:00 UTC2023-08-16 06:00:00 UTC000
Aug 16, 06:002023-08-16 06:00:00 UTC2023-08-16 12:00:00 UTC000
Aug 16, 12:002023-08-16 12:00:00 UTC2023-08-16 18:00:00 UTC000
Aug 16, 18:002023-08-16 18:00:00 UTC2023-08-17 00:00:00 UTC110
Aug 17, 00:002023-08-17 00:00:00 UTC2023-08-17 06:00:00 UTC000
Aug 17, 06:002023-08-17 06:00:00 UTC2023-08-17 12:00:00 UTC000
Aug 17, 12:002023-08-17 12:00:00 UTC2023-08-17 18:00:00 UTC110
Aug 17, 18:002023-08-17 18:00:00 UTC2023-08-18 00:00:00 UTC101
Aug 18, 00:002023-08-18 00:00:00 UTC2023-08-18 06:00:00 UTC000
Aug 18, 06:002023-08-18 06:00:00 UTC2023-08-18 12:00:00 UTC000
Aug 18, 12:002023-08-18 12:00:00 UTC2023-08-18 18:00:00 UTC000
Aug 18, 18:002023-08-18 18:00:00 UTC2023-08-19 00:00:00 UTC000
Aug 19, 00:002023-08-19 00:00:00 UTC2023-08-19 06:00:00 UTC000
Aug 19, 06:002023-08-19 06:00:00 UTC2023-08-19 12:00:00 UTC000
Aug 19, 12:002023-08-19 12:00:00 UTC2023-08-19 18:00:00 UTC000
Aug 19, 18:002023-08-19 18:00:00 UTC2023-08-20 00:00:00 UTC000
Aug 20, 00:002023-08-20 00:00:00 UTC2023-08-20 06:00:00 UTC000
Aug 20, 06:002023-08-20 06:00:00 UTC2023-08-20 12:00:00 UTC000
Aug 20, 12:002023-08-20 12:00:00 UTC2023-08-20 18:00:00 UTC000
Aug 20, 18:002023-08-20 18:00:00 UTC2023-08-21 00:00:00 UTC000
Aug 21, 00:002023-08-21 00:00:00 UTC2023-08-21 06:00:00 UTC000
Aug 21, 06:002023-08-21 06:00:00 UTC2023-08-21 12:00:00 UTC000
Aug 21, 12:002023-08-21 12:00:00 UTC2023-08-21 18:00:00 UTC000
Aug 21, 18:002023-08-21 18:00:00 UTC2023-08-22 00:00:00 UTC000
Aug 22, 00:002023-08-22 00:00:00 UTC2023-08-22 06:00:00 UTC000
Aug 22, 06:002023-08-22 06:00:00 UTC2023-08-22 12:00:00 UTC000
Aug 22, 12:002023-08-22 12:00:00 UTC2023-08-22 18:00:00 UTC101

What Hacker News says

5 sources
jawerty·Aug 22, 2023
Last night, after 8 hours, I was able to get this working OK. It looks at GitHub issues, finds related "APIs" to the GitHub issue and finds which files need to be fixed in a cloned repo, then updates them with WizardCoder. So far WizardCoder actually has solid reasoning compared to using the Llama 2 React Coder I made last week https://github.com/jawerty/10x-React-Engineer I highly suggest if you want to use 10x-React-Engineer you move the prompts to WizardCoder and load that LLM. Or I may just do it after I rest from this one. Overall this is my 3rd live streamed LLM Agent in the past week (check my latest videos) and seems like getting good reception. What should I build next?
In I Live Coded Building an LLM Agent That Contributes to GitHub Repos for You [video]
jawerty·Aug 17, 2023
Last night, I live streamed myself coding this Llama 2 Agent on a Single GPU (Colab). After 6 hours it actually has some good results. How it works is it takes in your intuition (e.g. "I think x would be cool") and develops a business idea (with a name and branding colors) and a business plan. After the business plan is developed, it criticizes this plan recursively until the "Investor" prompt is satisfied with the plan. After all this it will generate the final MVP idea and pass it to a the React Engineer Agent I live coded 2 days ago (https://github.com/jawerty/10x-react-engineer). Finally once the code is generated you have an option to pivot. As for the AI's memory, I have a small vector db for history of good intuition+idea examples to use as context (builds as you generate) and a simple backlog of business idea criticisms. Overall,
Read the rest
this experiment showed me that you definitely don't need OpenAI keys to have an effective LLM Agent for you. This is only using the Llama 13b parameter chat model and doing a wonderful job. I spend maybe 5 dollars of Colab compute building this for 6 hours which is way more than it would be to mess around with this. One caveat is the final react code base often needs some modifications to the package.json/webpack setup. However, It's generating the components/folder surprisingly well starting from the entrypoint file. I addressed most of these concerns in this video but still going to fine tune a model that's way better in my next video or just move to a fine-tuned starcoder for this portion. Let me know what you think and play around with the Colab if you can! The live stream: https://youtube.com/live/ZCyxDRSw0wE The 10X-React-Engineer: https://github.com/jawerty/10x-react-engineer If you want to see me live code more let me know any ideas you'd like to see built. I've been streaming projects like these most days this past month and don't feel like stopping haha.
In I Live Coded a Llama 2 Agent That Builds Startups from Your Inutitions [video]
deusrex·Aug 17, 2023Submission

Show HN: AutoStartup, A Llama 2 Agent That Plans and Builds Your Startup Ideas

Hi HN! Last night, I live streamed myself coding this Llama 2 Agent on a Single GPU (Colab). After 6 hours it actually has some good results. How it works is it takes in your intuition (e.g. "I think x would be cool") and develops a business idea (with a name and branding colors) and a business plan. After the business plan is developed, it criticizes this plan recursively until the "Investor" prompt is satisfied with the plan. After all this it will generate the final MVP idea and pass it to a the React Engineer Agent I live coded 2 days ago (https://github.com/jawerty/10x-react-engineer). Finally once the code is generated you have an option to pivot. As for the AI's memory, I have a small vector db for history of good intuition+idea examples to use as context (builds as you generate) and a simple backlog of business idea criticisms. Ov
Read the rest
erall, this experiment showed me that you definitely don't need OpenAI keys to have an effective LLM Agent for you. This is only using the Llama 13b parameter chat model and doing a wonderful job. I spend maybe 5 dollars of Colab compute building this for 6 hours which is way more than it would be to mess around with this. One caveat is the final react code base often needs some modifications to the package.json/webpack setup. However, It's generating the components/folder surprisingly well starting from the entrypoint file. I addressed most of these concerns in this video but still going to fine tune a model that's way better in my next video or just move to a fine-tuned starcoder for this portion. Let me know what you think and play around with the Colab if you can! The live stream: https://youtube.com/live/ZCyxDRSw0wE The 10X-React-Engineer: https://github.com/jawerty/10x-react-engineer If you want to see me live code more let me know any ideas you'd like to see built. I've been streaming projects like these most days this past month and don't feel like stopping haha.
5 points · Open discussion
jawerty·Aug 15, 2023Submission

Show HN: 10x-React-Engineer, Generate Entire React Codebases with Llama 2

Hi HN, Yesterday I live streamed myself for 6 hours building this from scratch. It’s an AI agent that uses Llama 2 (so far the 13b chat model) to generate a full react codebase from a single prompt. It had a “dev loop” that iterates on your feedback and resolves dependencies. In the end it kinda worked and I got excited so wanted to post here haha. Long story short a viewer on my discord suggested I build in of these and I just had to look into how these work (inspired by GPT Engineer and AutoGPT) I wanted to work on a more specific downstream task so I focused on web dev. Llama 2 isn’t the best option for this so I will look into utilizing a chat fine tuned starcoder or fine tune llama 2 myself for better results. In the end I spend only some compute units testing this 1000 times on a single gpu I had in Colab and has some pretty solid r
Read the rest
esults for iterating in a fairly short amount of time. Going to build upon this more in the coming weeks (clean the code…). Let me know what you think! Livestream: https://www.youtube.com/live/6_sdnYDmUmo?feature=share
13 points · Open discussion

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.