# LanceDB — API Agent Score

> Score: 79/100 (Grade: B) | Domain: lancedb.com | Rubric: 1.0.0 | Checked: July 24, 2026

LanceDB scored 79/100 (B), classified "partially-ready".

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

## Summary

- Overall: 79/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 94/100 (A+)
- Developer Experience: 63/100 (C)
- Agent Discovery: 98/100 (A+)
- Agent Understanding: 66/100 (C)
- Agent Usability: 74/100 (B)

## Check Results

### API Design

- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Schema coverage & depth — 158/160 (99%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 100%, spec 50%.
- [warn] Machine-readable, versioned contract — info.version="1.0.0" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, spec 0%, docs 0%.

### Developer Experience

- [pass] Quickstart present — Quickstart at https://docs.lancedb.com/quickstart with a runnable first-call sample. Investigated: docs 100%.
- [pass] Description completeness — 100% of operations + parameters have substantive descriptions. Investigated: spec 100%, sdk 74%.
- [pass] Changelog published — Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.
- [fail] Self-service developer portal — No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%.
- [fail] Code samples in docs — No detectable code samples across 20 sampled docs pages. Investigated: docs 0%.

### Agent Discovery

- [pass] Docs reachable, not hard auth-gated — All 50 sampled pages are publicly accessible. Investigated: docs 100%.
- [warn] llms.txt present, valid & comprehensive — llms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.lancedb.com/llms.txt: No blockquote summary found. Investigated: docs 94%, sdk 0%.
- [pass] Registry & SDK presence — Indexed on Context7 (websites/lancedb, 4406 snippets). Investigated: docs 100%, sdk 100%, cli 100%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — error codes documented in the docs site at https://docs.lancedb.com/geneva/udfs/error_handling. Investigated: docs 100%, spec 50%, sdk 0%.
- [warn] Agent-navigable, token-efficient docs — 1 of 50 pages have substantive content differences between markdown and HTML (avg 1% missing). Investigated: docs 90%.
- [pass] Docs structured data — JSON-LD Article markup on 19/19 assessed pages (100%) with dateModified present. Investigated: docs 100%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 3 surfaces (spec, docs, sdk) is 4% (threshold 35% for full credit).
- [fail] Operation purpose clarity — 0% of operations are agent-inferable. Investigated: spec 0%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Pagination documented & consistent — Pagination params detected on 1 list endpoint(s). Investigated: docs 100%, spec 75%.
- [pass] Sandbox separation — Sandbox server declared but no distinguishable test credentials in scheme descriptions. Investigated: spec 100%, docs 100%, sdk 100%.
- [fail] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 0%, docs 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

LanceDB's API program shows real strength in API design and documentation discovery — partners and agents can find and parse the contract reliably. The critical gaps are in agent understanding and partner onboarding: operations lack the semantic clarity and structured guidance agents need to build correctly without hallucinating, and partners have no self-service portal or inline code samples to get hands-on quickly. Closing these two areas should be the immediate priority to unlock autonomous partner integration and shorten the path from discovery to a successful first call.