Pricing

from $2.10 / 1,000 processed repositories

Try for free

Go to Apify Store

GitHub Repo to RAG Chunks & LLM Context

Try for free

Turn any public or private GitHub repo into token-counted, line-cited RAG chunks and one LLM-ready context file. One archive download, no API quota, secrets masked, license and commit included. Not affiliated with GitHub.

Pricing

from $2.10 / 1,000 processed repositories

Rating

0.0

(0)

Developer

Muhammet Mustafa Dincer

Actor stats

Bookmarked

Total users

Monthly active users

3 days ago

Last modified

Categories

Developer tools

Automation

Security

recordType

Optional

Row kind: repository (one per repository, always written), chunk (one per token-counted chunk, in chunks and both modes) or file (one per file with its whole text, in files and both modes).

Type:string

Example:

repository

Options:

repositorychunkfile

input

Optional

Repository rows only: the reference exactly as it was given. Stable between runs, so it works as a join key.

Type:string | null

Example:

https://github.com/expressjs/express

repository

Optional

owner/name of the repository. On repository rows this is null only when the reference could not be parsed.

Type:string | null

Example:

expressjs/express

url

Optional

Repository rows only: the repository home page.

Type:string | null

Example:

https://github.com/expressjs/express

status

Optional

Repository rows only: processed (files were read and charged), empty (downloaded, but no readable file matched, not charged) or failed (not charged).

Type:string | null

Example:

processed

failureReason

Optional

Repository rows only, when status is not processed: invalid_reference, not_found, token_rejected, blocked, too_large, network_error, http_error, corrupt_archive, unavailable_for_legal_reasons or no_readable_files.

Type:string | null

Example:

null

message

Optional

Repository rows only: a sentence that explains a failure, an empty result or skipped metadata. Null when everything worked.

Type:string | null

Example:

null

owner

Optional

Repository rows only: the account that owns the repository.

Type:string | null

Example:

expressjs

name

Optional

Repository rows only: the repository name.

Type:string | null

Example:

express

ref

Optional

Branch, tag or commit that was read. Null means the default branch was read (see defaultBranch and commitSha).

Type:string | null

Example:

null

commitSha

Optional

Exact commit the archive was built from. Chunk and file rows carry it too, and their sourceUrl is pinned to it, so a citation keeps pointing at the same text after the repository changes.

Type:string | null

Example:

a1b2c3d4e5f60718293a4b5c6d7e8f9012345678

subPath

Optional

Repository rows only: the folders the run was limited to, from the Folders input or a /tree/ link.

Type:string | null

Example:

null

description

Optional

Repository rows only: the About text of the repository. Needs includeMetadata and an available GitHub API.

Type:string | null

Example:

Fast, unopinionated, minimalist web framework for node.

stars

Optional

Repository rows only: stargazers at the time of the run.

Type:integer | null

Example:

65000

forks

Optional

Repository rows only: forks at the time of the run.

Type:integer | null

Example:

23000

openIssues

Optional

Repository rows only: open issues and pull requests.

Type:integer | null

Example:

150

topics

Optional

Repository rows only: topics set on the repository.

Type:array | null

Example:

express,nodejs

primaryLanguage

Optional

Repository rows only: the language GitHub reports as the main one.

Type:string | null

Example:

JavaScript

defaultBranch

Optional

Repository rows only: the default branch.

Type:string | null

Example:

master

pushedAt

Optional

Repository rows only: when the last push happened, ISO 8601.

Type:string | null

Example:

2026-10-30T09:12:44Z

archived

Optional

Repository rows only: true when the repository is archived (read-only).

Type:boolean | null

Example:

false

homepage

Optional

Repository rows only: the homepage URL set on the repository.

Type:string | null

Example:

https://expressjs.com

license

Optional

Repository rows only: SPDX identifier, detected from the LICENSE text or, if that is not recognised, taken from the GitHub API. A heuristic, not legal advice.

Type:string | null

Example:

MIT

licenseSource

Optional

Repository rows only: license_file or github_api, so you know how much to trust the license field.

Type:string | null

Example:

license_file

metadataStatus

Optional

Repository rows only: ok, unavailable (the GitHub API refused or was rate limited; the files are still complete) or disabled.

Type:string | null

Example:

fileCount

Optional

Repository rows only: files that were read and charged for.

Type:integer | null

Example:

archiveFileCount

Optional

Repository rows only: every file in the archive, before any filter.

Type:integer | null

Example:

212

chunkCount

Optional

Repository rows only: how many chunk rows this repository produced. Null in files mode.

Type:integer | null

Example:

120

tokenCount

Optional

Tokens in the file text (repository and file rows) or in the chunk text (chunk rows), counted with the cl100k_base tokenizer used by OpenAI models. On a repository row it is the total of the files read, before chunk overlap.

Type:integer | null

Example:

48210

charCount

Optional

Characters of text in this row.

Type:integer | null

Example:

161002

languages

Optional

Repository rows only: files and tokens per language, top 15 by tokens.

Type:object | null

Example:

[object Object]

skippedFiles

Optional

Repository rows only: how many files were left out and why: excluded_directory, lockfile, minified_or_generated, binary, too_large, empty, not_utf8_text, not_selected (outside your folders or patterns) or file_limit.

Type:object | null

Example:

[object Object]

truncated

Optional

Repository rows only: true when a limit stopped the run on this repository before every candidate file was read. truncatedReason says which limit.

Type:boolean | null

Example:

false

truncatedReason

Optional

Repository rows only: file_limit, chunk_limit, text_size_limit or budget (your maximum cost per run was reached).

Type:string | null

Example:

null

secretsRedacted

Optional

Repository rows: how many secret-looking values were replaced with [REDACTED:type] across the repository (null when redaction is off). File rows: the count for that file.

Type:integer | null

Example:

secretTypes

Optional

Repository rows only: which kinds of secrets were redacted.

Type:array | null

Example:

archiveBytes

Optional

Repository rows only: size of the downloaded archive.

Type:integer | null

Example:

1048576

directoryTree

Optional

Repository rows only: indented folder tree of the files that were read, capped at 300 lines.

Type:string | null

Example:

src/ index.js

contextFileKey

Optional

Repository rows only: key of the single-file Markdown digest in the run's key-value store.

Type:string | null

Example:

CONTEXT-expressjs-express.md

contextFileUrl

Optional

Repository rows only: link to that digest. One file, directory tree plus the files in reading order, ready to paste into an LLM.

Type:string | null

Example:

https://api.apify.com/v2/key-value-stores/abc/records/CONTEXT-expressjs-express.md

contextFileTokens

Optional

Repository rows only: tokens in the digest, always within contextTokenBudget.

Type:integer | null

Example:

98000

durationMs

Optional

Repository rows only: how long this repository took.

Type:integer | null

Example:

4210

scrapedAt

Optional

Repository rows only: when the row was written, ISO 8601.

Type:string | null

Example:

2026-11-04T10:00:00.000Z

path

Optional

Chunk and file rows: path inside the repository.

Type:string

Example:

lib/router/index.js

language

Optional

Chunk and file rows: language from the file name, or null when the type is not recognised.

Type:string | null

Example:

JavaScript

chunkIndex

Optional

Chunk rows: position of the chunk within its file, starting at 0.

Type:integer

Example:

fileChunkCount

Optional

Chunk rows: how many chunks the file produced.

Type:integer

Example:

text

Optional

Chunk rows: the chunk text. File rows: the whole file text (secrets redacted unless you turned that off).

Type:string

Example:

'use strict'...

lineStart

Optional

Chunk rows: first line of the chunk in the file, 1-based.

Type:integer

Example:

lineEnd

Optional

Chunk rows: last line of the chunk. Together with lineStart this is the citation.

Type:integer

Example:

citation

Optional

Chunk rows: path:lineStart-lineEnd, the string to show next to an answer.

Type:string

Example:

lib/router/index.js:1-42

sourceUrl

Optional

Chunk and file rows: GitHub link to the exact lines at the exact commit.

Type:string

Example:

https://github.com/expressjs/express/blob/a1b2c3d/lib/router/index.js#L1-L42

headings

Optional

Chunk rows from Markdown-like files: the headings the chunk sits under or contains.

Type:array | null

Example:

Installation

isPartial

Optional

Chunk rows: true when a single line was longer than the chunk size and had to be cut mid-line.

Type:boolean

Example:

false

sizeBytes

Optional

File rows: size of the file in the archive.

Type:integer

Example:

4120

lineCount

Optional

File rows: number of lines.

Type:integer

Example:

120

Instagram Scraper

apify/instagram-scraper

Extract Instagram posts, reels, profiles, places, hashtags, carousels, and comments. Get data from Instagram using one or more Instagram URLs or search queries: content, context, metrics, metadata. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Apify

467K

4.7

(604)

Google Maps Scraper

compass/crawler-google-places

Extract data from thousands of Google Maps locations and businesses, including reviews, reviewer details, images, contact info, including full name, email, and job title, opening hours, prices & more. Export data, run via API, schedule and monitor runs, or integrate with other tools.

Compass

682K

4.7

(1,825)

Instagram Profile Scraper

apify/instagram-profile-scraper

Scrape all Instagram profile info. Just add Instagram usernames, IDs or URLs and extract name, join date, number of followers, location, bio, website, related profiles, video&post count, latest posts. Export scraped data, schedule scraper via API, and integrate with other tools or AI workflows.

Apify

275K

4.7

(175)

TikTok Scraper

clockworks/tiktok-scraper

Extract data from TikTok videos, hashtags, and users. Use URLs or search queries to scrape TikTok profiles, hashtags, posts, URLs, shares, followers, hearts, names, video, and music-related data. Export scraped data, run the scraper via API, schedule and monitor runs or integrate with other tools.

Clockworks

380K

4.8

(370)

Google Search Results Scraper

apify/google-search-scraper

Scrape Google Search Engine Results Pages (SERPs). Select the country or language and extract organic and paid results, AI Mode, AI overviews, ads, queries, People Also Ask, prices, reviews, like a Google SERP API. Export data, run the scraper via API, schedule runs, or integrate with other tools.

Apify

227K

4.7

(218)

LinkedIn Profile Scraper + Email (No Cookies)

harvestapi/linkedin-profile-scraper

Extract detailed information from LinkedIn profiles in bulk, including complete work experience, education history, skills and more. No cookies or account required.

HarvestAPI

93K

4.6

(93)

Instagram Reel Scraper

apify/instagram-reel-scraper

Scrape or download Instagram reels. Just add Instagram profile or reel URL, and get caption, timestamp, transcript, hashtags, mentions, tagged users, comments, likes, shares, views, duration, and downloaded video. Export scraped data, schedule via API, and integrate with other tools or AI workflows.

Apify

185K

4.4

(102)

YouTube Scraper

streamers/youtube-scraper

YouTube crawler and video scraper. Alternative YouTube API with no limits or quotas. Extract and download channel name, likes, number of views, and number of subscribers.

Streamers

201K

4.8

(196)

Instagram Post Scraper

apify/instagram-post-scraper

Scrape Instagram posts. Just add one or more Instagram usernames and get your data in seconds including caption, metrics, images, mentions, coauthors, recent comments, sponsored status, video duration, views. Export scraped data, schedule scraper via API, integrate with other tools or AI workflows.

Apify

153K

4.3

(139)

Facebook Pages Scraper

apify/facebook-pages-scraper

Extract basic data from multiple Facebook Pages or Profiles. Extract Facebook page details, website, email, address, messenger, likes, followers, rating, ad running status, and other public data. Export scraped data, schedule scraper via API, integrate with other tools or AI workflows.

Apify

74K

4.7

(55)