{
"openapi": "3.0.1",
"info": {
"title": "GitHub Repo Scraper ยท Repositories, Stars, Topics & Languages",
"description": "Scrape GitHub repositories by language, topic, star count, license, organization, and pushed date window. Returns clean structured repo metrics and metadata without authentication.",
"version": "1.0",
"x-build-id": "UIni5bWIeJGyJxv2B"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/reapx~github-repo-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-reapx-github-repo-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/reapx~github-repo-scraper/runs": {
"post": {
"operationId": "runs-sync-reapx-github-repo-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/reapx~github-repo-scraper/run-sync": {
"post": {
"operationId": "run-sync-reapx-github-repo-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"required": [
"maxItems"
],
"properties": {
"query": {
"title": "Search Query / Filter",
"type": "string",
"description": "Custom GitHub repository search query expression (e.g. stars:>1000 language:python). Consequence: Broader queries increase run duration and total event charges; specific filters isolate exact targets.
Empty meaning: Leave empty to build query automatically from the language, topic, stars, license, and organization inputs below."
},
"language": {
"title": "Programming Language",
"type": "string",
"description": "Filter repositories by primary programming language (e.g., python, typescript, rust, go, java). Consequence: Narrows search results to codebases written in the chosen language.
Empty meaning: Leave empty to search across all programming languages unconditionally without language restriction."
},
"topic": {
"title": "Topic Tag",
"type": "string",
"description": "Filter repositories tagged with a specific GitHub topic (e.g., machine-learning, web3, cli, react). Consequence: Restricts returned items to repositories explicitly tagged with this topic.
Empty meaning: Leave empty to search across all topics and untagged repositories."
},
"minStars": {
"title": "Minimum Stars",
"minimum": 0,
"type": "integer",
"description": "Minimum stargazer count threshold for matching repositories (e.g., 500). Consequence: Higher minimum star values filter out lower-ranked or newly created repositories, focusing results on popular projects.
Empty meaning: Leave at 0 or empty for no lower bound on repository stars."
},
"maxStars": {
"title": "Maximum Stars",
"minimum": 0,
"type": "integer",
"description": "Maximum stargazer count ceiling for matching repositories (e.g., 5000). Consequence: Setting a maximum cap isolates mid-tier or hidden gem repositories before they reach viral star counts.
Empty meaning: Leave at 0 or empty for no upper bound on repository stars.
The higher the number, the longer the run takes and the more you are charged, because you pay per row returned."
},
"license": {
"title": "SPDX License Identifier",
"type": "string",
"description": "Filter by open-source license key (e.g., mit, apache-2.0, gpl-3.0, bsd-3-clause). Consequence: Filters repository records to projects with compatible open-source licensing.
Empty meaning: Leave empty to include repositories with any open-source license or no declared license."
},
"organization": {
"title": "GitHub Owner / Organization",
"type": "string",
"description": "Filter repositories belonging to a specific GitHub user or organization (e.g., facebook, google, vercel). Consequence: Restricts results strictly to public repositories owned by the specified organization or user account.
Empty meaning: Leave empty to search across all public GitHub organizations and user accounts."
},
"pushedAfter": {
"title": "Pushed After Date",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"type": "string",
"description": "Filter repositories with code commits pushed on or after this ISO date (e.g., 2026-01-01). Consequence: Excludes unmaintained or stale repositories that have not received recent updates.
Empty meaning: Leave empty to include repositories regardless of last commit push date."
},
"sort": {
"title": "Sort Criterion",
"enum": [
"stars",
"forks",
"help-wanted-issues",
"updated"
],
"type": "string",
"description": "Field by which search results are ordered by GitHub Search API (stars, forks, help-wanted-issues, updated). Consequence: Controls ranking priority of returned repository records.
Empty meaning: Defaults to sorting by stars.",
"default": "stars"
},
"order": {
"title": "Sort Direction",
"enum": [
"desc",
"asc"
],
"type": "string",
"description": "Sort direction for ordering query results (desc for descending order, asc for ascending order). Consequence: Directs whether top-ranked or bottom-ranked repositories appear first in returned items.
Empty meaning: Defaults to desc (descending).",
"default": "desc"
},
"maxItems": {
"title": "Maximum Repositories to Scrape",
"minimum": 1,
"maximum": 5000,
"type": "integer",
"description": "Maximum number of repository records to scrape and output into dataset (e.g., 50, 500). Consequence: Higher numbers increase execution runtime and pay-per-event cost at $0.001 per record.
Empty meaning: Defaults to 50 repository items.
The higher the number, the longer the run takes and the more you are charged, because you pay per row returned.",
"default": 50
},
"githubToken": {
"title": "GitHub Personal Access Token (Optional)",
"type": "string",
"description": "Optional GitHub PAT for higher rate limits (30 req/min for Search API instead of 10 req/min unauthenticated). Consequence: Significantly speeds up multi-page queries; never stored or logged.
Empty meaning: Runs unauthenticated with automatic backoff pacing."
}
}
},
"runsResponseSchema": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"actId": {
"type": "string"
},
"userId": {
"type": "string"
},
"startedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"finishedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"status": {
"type": "string",
"example": "READY"
},
"meta": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"example": "API"
},
"userAgent": {
"type": "string"
}
}
},
"stats": {
"type": "object",
"properties": {
"inputBodyLen": {
"type": "integer",
"example": 2000
},
"rebootCount": {
"type": "integer",
"example": 0
},
"restartCount": {
"type": "integer",
"example": 0
},
"resurrectCount": {
"type": "integer",
"example": 0
},
"computeUnits": {
"type": "integer",
"example": 0
}
}
},
"options": {
"type": "object",
"properties": {
"build": {
"type": "string",
"example": "latest"
},
"timeoutSecs": {
"type": "integer",
"example": 300
},
"memoryMbytes": {
"type": "integer",
"example": 1024
},
"diskMbytes": {
"type": "integer",
"example": 2048
}
}
},
"buildId": {
"type": "string"
},
"defaultKeyValueStoreId": {
"type": "string"
},
"defaultDatasetId": {
"type": "string"
},
"defaultRequestQueueId": {
"type": "string"
},
"buildNumber": {
"type": "string",
"example": "1.0.0"
},
"containerUrl": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "integer",
"example": 1
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
},
"usageTotalUsd": {
"type": "number",
"example": 0.00005
},
"usageUsd": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "number",
"example": 0.00005
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
}
}
}
}
}
}
}
}