# Opencode — API Agent Score

> Score: 75/100 (Grade: B) | Domain: opencode.ai | Rubric: 1.0.0 | Checked: October 28, 2026

Opencode scored 75/100 (B), classified "partially-ready".

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

## Summary

- Overall: 75/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 94/100 (A+)
- Developer Experience: 68/100 (C)
- Agent Discovery: 73/100 (B)
- Agent Understanding: 92/100 (A+)
- Agent Usability: 56/100 (D)

## Check Results

### API Design

- [pass] Schema coverage & depth — 3/3 enums are named types (not bare strings). Investigated: sdk 100%, spec 50%.
- [pass] Auth declared & discoverable — This API requires no credentials and says so — the spec declares `security: []`, meaning no credentials are required (spec). An agent can call it directly. Investigated: spec 100%, docs 100%, mcp 100%, cli 0%.
- [warn] Machine-readable, versioned contract — The API sets a version ("1.0.0") but exposes no versioning scheme in the URL, a header, or the media type, so an agent can't pin to a specific version. Investigated: spec 75%, docs 50%, cli 0%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, sdk 83%, wellknown 0%.
- [pass] Example coverage — Docs show code samples in 4 language(s) (top: shell, javascript, typescript), and 10 of 20 sampled pages offer ≥ 2 languages side by side. Investigated: docs 100%, sdk 100%, spec 0%, cli 0%.

### Developer Experience

- [pass] Self-service developer portal — The API requires no credentials (the spec declares `security: []`, meaning no credentials are required (spec)), so there is nothing to sign up for and no sales gate to clear. Investigated: docs 100%.
- [pass] Code samples in docs — Docs show code samples in 4 language(s) (top: shell, javascript, typescript), and 10 of 20 sampled pages offer ≥ 2 languages side by side. Investigated: docs 100%.
- [pass] Changelog published — changelog is documented on the docs site at https://opencode.ai/changelog, even though it isn't declared in the API spec. Investigated: spec 100%, docs 100%.
- [fail] Quickstart present — No quickstart or getting-started page found at the conventional docs paths, so new developers and agents have no obvious first step. Investigated: docs 0%.
- [fail] Description completeness — Only 33% of operations and parameters have descriptions (124 of 187 ops, 0 of 414 params), leaving an agent to guess what most endpoints do. Investigated: spec 0%.

### Agent Discovery

- [pass] Docs reachable, not hard auth-gated — All 1 pages are publicly accessible. Investigated: docs 100%.
- [pass] Registry & SDK presence — Indexed on Context7 (anomalyco/opencode, 11195 snippets). Investigated: docs 100%, cli 100%, sdk 50%, mcp 0%, wellknown 0%.
- [warn] Crawlable / AEO — Sitemap has 706 entries but no lastmod values, so crawlers can't tell what changed recently. Investigated: wellknown 75%.
- [fail] llms.txt present, valid & comprehensive — No llms.txt found at any candidate location (https://opencode.ai/docs/llms.txt, https://opencode.ai/llms.txt); 1 failed to fetch. Investigated: docs 0%, sdk 0%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Documents 7 distinct 4xx/5xx error response codes, so an agent can branch on specific failures instead of guessing. Investigated: docs 100%, spec 50%, cli 0%.
- [pass] Operation purpose clarity — 94% of operations (175 of 187) have both a clear summary and a descriptive name, so an agent can pick the right endpoint. Investigated: spec 100%.
- [pass] Agent-navigable, token-efficient docs — All 1 pages contain server-rendered content. Investigated: docs 100%.
- [warn] Agent instructions file (AGENTS.md) — No agents.md or skill.md context file found (nice-to-have for agent operation). Investigated: sdk 50%, cli 0%, wellknown 0%.
- [warn] Docs structured data — Only OpenGraph/meta tags across 3 assessed pages — no JSON-LD for AI answer engines to cite. Investigated: docs 50%.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Pagination documented & consistent — Pagination parameters are present on the 50 list endpoint(s), so an agent can page through results. Investigated: spec 100%, docs 100%.
- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%, spec 0%, docs 0%.
- [pass] Runnable collection with test scripts — README is present and includes a runnable quickstart. Investigated: sdk 100%, platform 0%.
- [fail] Idempotency documented — Only 0% of mutating operations (0 of 100) document idempotency, so an agent's retries can create duplicate writes. Investigated: spec 0%, docs 0%, sdk 0%, cli 0%.
- [fail] Rate-limit signaling — No rate-limit response headers are documented, so an agent can't tell when it is approaching a limit and will get throttled. Investigated: spec 0%, docs 0%.

## Executive Summary

Opencode's API program has a standout strength in agent understanding and API contract quality, giving AI agents a reliable surface to build against. However, two areas need urgent attention: developer experience is undermined by sparse descriptions across the vast majority of endpoints and parameters, and agent usability is critically weakened by the complete absence of idempotency guidance and rate-limit signaling — meaning agents retrying mutating operations risk silent data duplication, and have no signal before they get throttled. Prioritize enriching the API contract with descriptions and reliability guardrails first, then establish the discoverable front door that lets partners and agents find and onboard to your APIs without friction.