Pricing

from $2.00 / 1,000 packed codebase files

Try for free

Go to Apify Store

GitHub Repo Codebase Packer: LLM Context & Tokens

Try for free

Pack GitHub repositories, source files, and docs into clean LLM-ready context with token counting, path filtering, and file tree visualization.

Pricing

from $2.00 / 1,000 packed codebase files

Rating

0.0

(0)

Developer

Lakshay Papneja

Actor stats

Bookmarked

Total users

Monthly active users

18 hours ago

Last modified

GitHub Repo Codebase Packer: LLM Context & Tokens (v1.0)

Pack entire GitHub repositories, documentation folders, and source trees into a single, clean LLM-ready context prompt formatted for Claude 3.5 Sonnet, ChatGPT, DeepSeek, and Cursor.

Built for AI engineers, autonomous coding agents, and developers who need to feed full multi-file codebases into LLMs without copy-pasting hundreds of individual files.

⚡ Key Capabilities

Automated Git Tree Traversal: Recursively scans full GitHub repository trees via official GitHub tree endpoints.
Token Estimation: Pre-computes estimated token counts per file (Math.ceil(chars / 3.8)) and for the entire assembled prompt.
Smart Path & Lockfile Filtering: Automatically ignores node_modules, .git, build output (dist/, build/), and lockfiles (package-lock.json, pnpm-lock.yaml) to conserve token limits.
Extension Targeting: Filter specifically by language (e.g. .ts, .py, .go, .rs, .md).
Dual Outputs:
1. Default Dataset: Every file as an individual record with metadata, token counts, and source code.
2. LLM_PROMPT.md in Key-Value Store: Ready-to-copy markdown document featuring an ASCII file tree and fenced code blocks.

⚙️ Input Parameters

Field	Type	Default	Description
`repoUrls`	`array`	`["https://github.com/expressjs/express"]`	List of GitHub repository URLs or `owner/repo` strings.
`branch`	`string`	`""`	Target branch or tag (defaults to repo default).
`extensions`	`array`	`[".js", ".ts", ".py", ...]`	Allowed extensions to include in prompt.
`maxFileSizeKb`	`integer`	`100`	Max file size in KB to prevent huge bundle files from polluting context.
`maxFiles`	`integer`	`150`	Maximum source files to extract (up to 1,000).
`excludePaths`	`array`	`["node_modules", ".git", ...]`	Directories or paths to exclude.

📦 Sample Dataset Output

{
  "repo": "expressjs/express",
  "path": "lib/express.js",
  "extension": ".js",
  "sizeBytes": 3240,
  "linesCount": 112,
  "estimatedTokens": 850,
  "rawUrl": "https://raw.githubusercontent.com/expressjs/express/master/lib/express.js",
  "scrapedAt": "2026-10-31T20:56:00.000Z"
}

Github Repo User Scraper

inquisitive_sarangi/github-repo-scraper

Github Repo User Scraper is simple tool to extract users of a repo(s) like contributors, stargazers & watchers. You can also export listings to JSON/CSV or any other as format.

API Master

GitHub Scraper - Repos, Stars, Forks and Users

dami_studio/github-scraper

GitHub scraper: search repos and users with the query you would type into GitHub's search box, or paste a list of usernames or repos. Repository rows give stars, forks, issues, language, topics, licence and dates; user rows give name, bio, company, location and followers. $0.90 per 1,000 rows.

Dami's Studio

5.0

(2)

Github Trending Scraper

mohamedgb00714/github-trending-scraper

github trending scraper

mohamed el hadi msaid

Github Users Scraper

dtrungtin/github-users-scraper

Github Users Scraper is an Apify actor for extracting users or emails from Github. It allows you to extract all watchers, stargazers, and members from a repository page.

Tin

278

4.0

(1)

GitHub Issues Scraper

incontrovertible_gate/github-issues-actor

Scrape issues from any public GitHub repo - no API token needed. Get titles, authors, labels, dates & more. Perfect for competitor analysis, market research & lead generation. Fast, reliable, 25 issues/sec.

Netsrac

Github Contributors Scraper

janbuchar/github-contributors-scraper

Jan Buchar

5.0

(1)

GitHub Repos Scraper

gio21/github-repos-scraper

Search and scrape GitHub repositories. Extract stars, forks, language, license, topics, and more from the GitHub public API.

Gio

GitHub Scraper - Repo Code, Docs & Metadata to LLM Text

get_anything/github-repo-scraper

Chat with a repo: turn any GitHub repository into LLM-ready text - README, file tree and source files as clean text with token counts, plus repo metadata and optional issues. Feed a codebase to ChatGPT/Claude or a RAG pipeline. Official GitHub API, no token required. Export JSON, CSV or Markdown.

Get Anything

GitHub Repository Scraper

skystone_labs/github-repo-scraper

Extract GitHub repository metadata using GitHub API and scraping. Get repo info, stars, forks, language, topics, and README content. Perfect for research, analysis, and building datasets.