# GitHub — API Agent Score

> Score: 77/100 (Grade: B) | Domain: github.com | Rubric: 1.0.0 | Checked: July 23, 2026

GitHub scored 77/100 (B), classified "partially-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/github)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 77/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 79/100 (B)
- Developer Experience: 75/100 (B)
- Agent Discovery: 81/100 (A)
- Agent Understanding: 82/100 (A)
- Agent Usability: 71/100 (B)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Versioning declared (info.version="1.1.4") and media-type-versioning detected. Investigated: spec 100%, docs 100%.
- [pass] Schema coverage & depth — 5/5 (100%) public params are fully typed (no any/**kwargs). Analyzer confirms all methods have a derivable input schema. Investigated: sdk 100%, spec 67%.
- [pass] Security & governance hygiene — security.txt valid at https://github.com/.well-known/security.txt (Contact + unexpired Expires). Investigated: wellknown 100%, spec 0%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, spec 0%.
- [fail] Auth declared & discoverable — No securitySchemes declared. Investigated: spec 0%, docs 0%.

### Developer Experience

- [pass] Self-service developer portal — Signup page at https://github.com/sign-up; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Description completeness — 98% of operations + parameters have substantive descriptions. Investigated: spec 100%, sdk 74%.
- [pass] Changelog published — Newest official SDK activity 1 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.
- [fail] Quickstart present — No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.
- [skip] Code samples in docs — No surface produced evidence for this capability in this run.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/github_en, 43828 snippets). Investigated: docs 100%, sdk 100%, cli 0%.
- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/50 sampled pages return markdown); 50 rate-limited (HTTP 429). Investigated: docs 75%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt directive found in HTML of any of 50 sampled pages. Investigated: docs 71%, sdk 0%.
- [warn] Crawlable / AEO — No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 50%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — 15 distinct 4xx/5xx response codes documented. Investigated: docs 100%, spec 50%, sdk 0%.
- [pass] Operation purpose clarity — 100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Agent-navigable, token-efficient docs — No sampled pages support .md URLs (0/50 tested). Investigated: docs 63%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Docs structured data — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 0 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Rate-limit signaling — 3 distinct rate-limit response headers documented. Investigated: spec 100%, docs 100%.
- [pass] Pagination documented & consistent — Pagination params detected on 241 list endpoint(s). Investigated: spec 100%, docs 100%, sdk 100%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.
- [fail] Idempotency documented — 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%, sdk 0%.
- [fail] Runnable collection with test scripts — No test scripts found in the workspace's collections. Investigated: platform 0%.

## Executive Summary

GitHub's API program performs well on discoverability and doc parseability, but has two critical gaps that directly limit partner and agent success: agents lack structured instructions to understand how to navigate and use the API surface, and there is no runnable, test-backed collection giving partners and their coding agents a verified, executable starting point. Prioritizing an agent instructions file and a runnable collection with test scripts will unblock both human partners and AI-driven integrations from day one — followed by closing the auth declaration and quickstart gaps to compress the time to a partner's first production call.