HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
kesor
chatgpt-code-plugin
TypeScript2023–2023
kesor / chatgpt-code-plugin

chatgpt-code-plugin

Code ChatGPT Plugin is a TypeScript Code Analyzer that enables ChatGPT to "talk" with YOUR code

2Distinct people
4Mentions
0Explicit recommenders
239GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Code ChatGPT Plugin is a TypeScript Code Analyzer that enables ChatGPT to "talk" with YOUR code

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, 12:54:37 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 day4 dated mentions

Observed mentions: 2023-05-27 23:33:23 UTC to 2023-06-11 06:11:39 UTC.

012023-05-27 00:00:00 UTC to 2023-05-28 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsMay 272023-05-28 00:00:00 UTC to 2023-05-29 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-05-29 00:00:00 UTC to 2023-05-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-05-30 00:00:00 UTC to 2023-05-31 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-05-31 00:00:00 UTC to 2023-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-01 00:00:00 UTC to 2023-06-02 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-02 00:00:00 UTC to 2023-06-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-03 00:00:00 UTC to 2023-06-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsJun 32023-06-04 00:00:00 UTC to 2023-06-05 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-05 00:00:00 UTC to 2023-06-06 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-06-06 00:00:00 UTC to 2023-06-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-07 00:00:00 UTC to 2023-06-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-08 00:00:00 UTC to 2023-06-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-09 00:00:00 UTC to 2023-06-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-10 00:00:00 UTC to 2023-06-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-06-11 00:00:00 UTC to 2023-06-12 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJun 11

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
May 272023-05-27 00:00:00 UTC2023-05-28 00:00:00 UTC110
May 282023-05-28 00:00:00 UTC2023-05-29 00:00:00 UTC101
May 292023-05-29 00:00:00 UTC2023-05-30 00:00:00 UTC000
May 302023-05-30 00:00:00 UTC2023-05-31 00:00:00 UTC000
May 312023-05-31 00:00:00 UTC2023-06-01 00:00:00 UTC000
Jun 12023-06-01 00:00:00 UTC2023-06-02 00:00:00 UTC000
Jun 22023-06-02 00:00:00 UTC2023-06-03 00:00:00 UTC000
Jun 32023-06-03 00:00:00 UTC2023-06-04 00:00:00 UTC000
Jun 42023-06-04 00:00:00 UTC2023-06-05 00:00:00 UTC000
Jun 52023-06-05 00:00:00 UTC2023-06-06 00:00:00 UTC101
Jun 62023-06-06 00:00:00 UTC2023-06-07 00:00:00 UTC000
Jun 72023-06-07 00:00:00 UTC2023-06-08 00:00:00 UTC000
Jun 82023-06-08 00:00:00 UTC2023-06-09 00:00:00 UTC000
Jun 92023-06-09 00:00:00 UTC2023-06-10 00:00:00 UTC000
Jun 102023-06-10 00:00:00 UTC2023-06-11 00:00:00 UTC000
Jun 112023-06-11 00:00:00 UTC2023-06-12 00:00:00 UTC101

What Hacker News says

4 sources
My version of loading multiple files into the context allows the UI of ChatGPT to load the files on his own, when it decides that it needs/wants to read the content of the file. And from some experimentation it would seem that each file it loads, it considers it as a separate interaction. Thus the token limit is much less of a problem, allowing to load larger pieces of code - either the whole thing, or piece by piece. https://github.com/kesor/chatgpt-code-plugin
In Show HN: Tiny Code Improver
Super interesting project! I like that you're exposing the structure of the git repo to GPT, and helping it understand and access the code in a semantically meaningful way via the function definition APIs. I've been working on similar things with GPT, but in a language agnostic way. That makes things a bit trickier, having to parse arbitrary source code languages. I was curious how you were parsing/lexing the files to pull out functions. I asked GPT about your repo, to see if I might find some useful tools for my project. It provided the helpful summary below. Looks like you're using typescript-estree to parse the code? $ git clone https://github.com/kesor/chatgpt-code-plugin.git $ cd chatgpt-code-plugin $ aider Using git repo: .git Use /help to see in-chat commands. >>> how does this package find and index all the functions
Read the rest
? This package finds and indexes all the functions using the following process: 1 It starts by getting a list of all the files in the project using the getFileList function in src/function-utils.ts. This function recursively traverses the directories and returns an array of file paths. 2 For each file in the list, the getFunctionList function in src/function-utils.ts is called. This function reads the file content and parses it into an Abstract Syntax Tree (AST) using a TypeScript parser. 3 The findFunctionsInFile function in src/function-utils.ts is then called with the AST as an argument. This function traverses the AST and identifies function declarations, function expressions, and class methods. It collects information about each function, such as its name, start and end positions, and stores it in an array. 4 Finally, the package returns an array of objects containing information about all the functions found in the project. This array can be used to index the functions and perform further operations, such as retrieving the function's code or analyzing its structure. >>> does it use any pre-built packages for this? or is it all homebrew? Yes, this package uses some pre-built packages to achieve its functionality. Here are the main ones: 1 @typescript-eslint/typescript-estree: This package is used to parse TypeScript code into an Abstract Syntax Tree (AST). It is used in the getFunctionList function to parse the file content and generate an AST. 2 fs: This is a built-in Node.js module for working with the file system. It is used to read directories, read file content, and check file stats. 3 ignore: This package is used to filter out files and directories based on the rules specified in the .gitignore file. It is used in the getFileList function to exclude files and directories that should not be processed. 4 path: This is a built-in Node.js module for working with file and directory paths. It is used to join and resolve paths, and to get relative paths. These pre-built packages are combined with custom code to find and index all the functions in the project.
In Show HN: No more copy-pasting – a ChatGPT plugin to read code from your computer
kesor·May 27, 2023Submission

Show HN: No more copy-pasting – a ChatGPT plugin to read code from your computer

Introducing the Code ChatGPT Plugin - a new era of seamless interaction between ChatGPT and your codebase. This TypeScript Code Analyzer furnishes a suite of utilities to analyze TypeScript code, enabling ChatGPT to "talk" with YOUR code. Fetch a list of all the files in your project, list of every function in a TypeScript or JavaScript file, or even get the content of a specific function, all while staying in your conversation with ChatGPT. With accessible API endpoints, you can effortlessly navigate your codebase and ask ChatGPT anything you can think of about it. Say goodbye to the days of incessant copy-pasting and welcome a more streamlined code discussion experience . I'd love to hear your thoughts, experiences, and suggestions for improvement. Let's discuss and evolve this tool together!
46 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.