GitHub Repository Search — Repos to JSON

Search GitHub repositories by keyword or qualifier and get stars, language, activity, issues and URL as JSON — $0.003 per repo.

Whether you are vetting a dependency, tracking a competitor’s open-source, or finding tools for a build, the signal is in the repo metadata: stars, recency, issue load. This actor turns a GitHub search into structured repo records so developer and research agents can rank and vet repositories without parsing HTML.

What this actor does

• Search GitHub repositories with full query-qualifier support (language:, stars:, topic:, …)
• Each result: full name, description, stars, language, forks, open issues, last-push + created dates, URL
• Filter by keyword/postedAfter; sorted by stars by default
• Batch many queries per run; cap spend with maxResults
• Unauthenticated (no token/setup) — best for targeted searches; large batches may hit GitHub's public rate limit

You only pay for successful results — failed or empty lookups cost nothing.

Why pick this Actor

• Flat repo records with stars, forks, open issues, language, and last-push date — ranking-pipeline-ready without parsing GitHub's nested API shapes
• Per-result pricing ($0.003/result) with a hard maxResults spend cap — empty lookups cost $0
• Flat, stable JSON schema with sourceUrl + scrapedAt on every item — citation-ready for RAG and grounding
• Batch many queries in one run; overlapping results are deduplicated and charged once
• MCP server, OpenAPI schema, and LangChain/CrewAI tool support out of the box — no glue code

Sample output

Each dataset item is flat, typed JSON with a sourceUrl and scrapedAt for citation/grounding:

{
  "query": "ai agent",
  "source": "github",
  "title": "NousResearch/hermes-agent",
  "stars": 190459,
  "language": "Python",
  "pushedAt": "2026-06-11T09:30:15.000Z",
  "url": "https://github.com/NousResearch/hermes-agent",
  "sourceUrl": "https://api.github.com/search/repositories?q=ai+agent",
  "scrapedAt": "2026-06-11T09:00:00.000Z"
}

Input

{"queries":["ai agent"]}

Field	Type	Description
queries / query	array / string	GitHub search query. One or many.
maxResults	integer	Hard spend cap (billed per result).
keywords / postedAfter	filters	Narrow results; enable delta/scheduled runs.

How much does it cost

Pay-per-result: $0.003 per successful result. No subscription, no compute-unit guesswork, no charge for empty results. An orchestrator can cap spend with maxResults.

How to use it with AI agents (MCP), Claude, and the API

Claude Desktop / Claude Code via Apify MCP

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": ["-y", "@apify/actors-mcp-server", "--actors", "oblanceolate_mandola/github-repo-search"],
      "env": { "APIFY_TOKEN": "<YOUR_APIFY_TOKEN>" }
    }
  }
}

Python (Apify API)

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("oblanceolate_mandola/github-repo-search").call(run_input={"queries":["ai agent"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

TypeScript (Apify API)

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('oblanceolate_mandola/github-repo-search').call({"queries":["ai agent"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

LangChain / CrewAI tool

from langchain_apify import ApifyActorsTool
tool = ApifyActorsTool("oblanceolate_mandola/github-repo-search")  # agent calls it autonomously

OpenAPI schema for self-integrating GPT agents is auto-exposed at the Actor's API tab.

Data & compliance

Reads only publicly accessible endpoints. No login, no credential harvesting, no CAPTCHA bypass. Every result carries its sourceUrl so downstream agents can cite and re-verify.

FAQ

Do I need a GitHub account or token?

No — this actor uses GitHub's public unauthenticated search, so there is no setup. Public search is rate-limited (~10 requests/min), which is plenty for targeted queries; for very large batches, run them in smaller scheduled chunks.

Can I use search qualifiers?

Yes — anything GitHub search supports, e.g. "language:go stars:>500 pushed:>2026-01-01".

How are results ordered?

By stars, descending, so the most prominent repositories come first.

Can AI agents call this Actor directly?

Yes — via the Apify MCP server (snippet above), the OpenAPI schema on the Actor's API tab, or the LangChain/CrewAI tool wrapper. Results are flat JSON with sourceUrl and scrapedAt on every item, so downstream agents can cite and re-verify.

What happens when there are no results?

You pay nothing. Billing is per dataset item delivered, so an empty lookup costs $0, and the run log states why (no match, source rate limit) instead of failing silently.

Changelog

• 1.0 — Initial release: github.