HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
context-labs
autodoc
TypeScript2023–2023
context-labs / autodoc

autodoc

Experimental toolkit for auto-generating codebase documentation using LLMs

3Distinct people
4Mentions
0Explicit recommenders
2.4KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Experimental toolkit for auto-generating codebase documentation using LLMs

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 hour4 dated mentions

Observed mentions: 2023-03-25 00:44:52 UTC to 2023-03-25 03:38:32 UTC.

0122023-03-25 00:00:00 UTC to 2023-03-25 01:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsMar 25, 00:002023-03-25 01:00:00 UTC to 2023-03-25 02:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsMar 25, 01:002023-03-25 02:00:00 UTC to 2023-03-25 03:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2023-03-25 03:00:00 UTC to 2023-03-25 04:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMar 25, 03:00

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
Mar 25, 00:002023-03-25 00:00:00 UTC2023-03-25 01:00:00 UTC110
Mar 25, 01:002023-03-25 01:00:00 UTC2023-03-25 02:00:00 UTC000
Mar 25, 02:002023-03-25 02:00:00 UTC2023-03-25 03:00:00 UTC202
Mar 25, 03:002023-03-25 03:00:00 UTC2023-03-25 04:00:00 UTC101

What Hacker News says

4 sources
Hallucination is definitely a problem but can be somewhat mitigated by good prompting. GPT-4 seems less prone to hallucination. This will be better over time. You can view the prompts used for generating docs here[1] and the prompts used for answering questions here[2] [1]https://github.com/context-labs/autodoc/blob/master/src/cli/... [2https://github.com/context-labs/autodoc/blob/master/src/cli/...]
In Autodoc: Toolkit for auto-generating codebase documentation using LLMs
Most interesting part to me, the prompts: https://github.com/context-labs/autodoc/blob/83f03a3cee62d6e... > You are acting as a code documentation expert for a project called ${projectName}. Below is the code from a file located at \`${filePath}\`. Write a detailed technical explanation of what this code does. Focus on the high-level purpose of the code and how it may be used in the larger project. Include code examples where appropriate. Keep you response between 100 and 300 words. DO NOT RETURN MORE THAN 300 WORDS. Output should be in markdown format. Do not say "this file is a part of the ${projectName} project". Do not just list the methods and classes in this file. Code: ${fileContents} Response:
In Autodoc: Toolkit for auto-generating codebase documentation using LLMs

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.