# Agora — API Agent Score

> Score: 63/100 (Grade: C) | Domain: agora.io | Rubric: 1.0.0 | Checked: July 24, 2026

Agora scored 63/100 (C), classified "partially-ready".

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

## Summary

- Overall: 63/100 (C)
- Classification: partially-ready

## Category Scores

- API Design: 87/100 (A)
- Developer Experience: 71/100 (B)
- Agent Discovery: 85/100 (A)
- Agent Understanding: 49/100 (F)
- Agent Usability: 45/100 (F)

## Check Results

### API Design

- [pass] Schema coverage & depth — package.json "types" → dist/esm/index.d.ts. Investigated: sdk 100%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.
- [warn] Security & governance hygiene — security.txt present but missing Contact; missing or expired Expires. Investigated: wellknown 50%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Self-service developer portal — Signup page at https://www.agora.io/en/; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Changelog published — Newest official SDK activity 1 day(s) ago. Investigated: sdk 100%.
- [warn] Quickstart present — Quickstart page reachable (24 variants scanned starting at https://docs.agora.io/en/quickstart) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%.
- [fail] Code samples in docs — No detectable code samples across 20 sampled docs pages. Investigated: docs 0%.
- [skip] Description completeness — No surface produced evidence for this capability in this run.

### Agent Discovery

- [pass] llms.txt present, valid & comprehensive — llms.txt found at https://docs.agora.io/llms.txt. Investigated: docs 100%, sdk 0%.
- [pass] Registry & SDK presence — Indexed on Context7 (websites/agora_io_en, 80273 snippets). Investigated: docs 100%, sdk 67%, cli 0%.
- [warn] Docs reachable, not hard auth-gated — 50 of 50 sampled pages return 200 for non-existent URLs (soft 404). Investigated: docs 50%.
- [warn] Crawlable / AEO — Sitemap present (3122 entries) but carries no lastmod values. Investigated: wellknown 75%.

### Agent Understanding

- [warn] Agent-navigable, token-efficient docs — 29 of 50 pages have substantive content differences between markdown and HTML (avg 38% missing). Investigated: docs 50%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 3 assessed pages (3 JS-rendered). Investigated: docs 0%.
- [skip] Machine-readable errors (RFC 9457) — No surface produced evidence for this capability in this run.
- [skip] Operation purpose clarity — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%.
- [fail] Idempotency documented — No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Agora's API program shows strong discoverability and auth fundamentals, but partners and their AI agents face significant friction in three areas: a lack of machine-readable context files and structured documentation that agents can parse without guessing, missing runnable examples with test coverage that let agents validate real workflows, and an undocumented idempotency model that exposes partners to unsafe integration patterns. Closing these gaps — starting with agent-readable documentation and runnable truth — will materially reduce integration failure rates and unblock both human partners and the AI-assisted development workflows they increasingly rely on.