I built an API that stops AI hallucinating colour

A developer launched Colour Memory, an API that maps hex values, palettes, and images to named archive colours with provenance data, CIEDE2000 distance, WCAG contrast, and cultural risk flags. The tool provides 65 REST endpoints and MCP integrations for LLMs and design systems, offering a public rate-limited demo key with no signup required. The API aims to eliminate AI hallucination of colour names by returning only archive-verified entries with confidence scores and do-not-say guardrails.

Colour intelligence for agents and design systems. Maps hex values, palettes, and images to named archive colours. Returns CIEDE2000 distance, Lab/LCh metrics, WCAG contrast, cultural risk, provenance, and design tokens. No signup to try it. → Public rate-limited demo key — safe to use in client examples Architecture 1Archive layerStructured colour records with names, primary sources, notes, and hex values drawn from historical and cultural archives. 3Agent layer65 REST endpoints and MCP tools for LLMs, design systems, and automated workflows. 4Narrative layerOptional LLM-generated reports, hooks, and briefs — clearly labelled where used. 1 Authentication Your demo key No signup. The demo key is rate-limited to 50 calls but covers everything below. Get a production key at colourmemory.com when you're ready to build. API Key cm demo public quickstart Pass as header: X-Api-Key: cm demo public quickstart · Public, rate-limited, safe to expose in client examples. 2 Tool 1 of 3 query.hex Match any hex to the archive. Returns the nearest named colour with its primary source, confidence score, claim role, and do not say guardrails. This is the core of what Colour Memory does. curl curl -X POST https://api.colourmemory.com/query/hex \ -H "X-Api-Key: cm demo public quickstart" \ -H "Content-Type: application/json" \ -d '{"hex": " D4A829", "n results": 1}' Response — key fields nameSong Gold Sycee archiveChina primary sourceNorthern Song Dynasty monetary records, 960–1127 confidence0.92 claim strengthA — Direct institutional record claim roleanchor do not say Do not describe this hex as spectrophotometrically measured — values are computed from material descriptions. claim role tells you how hard you can push this entry: anchor = load-bearing evidence. reject = stub, exclude from deliverables. 3 Tool 2 of 3 archive.search Full-text keyword search across thousands of archive colours. This is a text search, not a colour search — search for "arterial blood" not "red". Use query.hex for hue-based retrieval. curl curl -X POST https://api.colourmemory.com/archive/search \ -H "X-Api-Key: cm demo public quickstart" \ -H "Content-Type: application/json" \ -d '{"query": "arterial blood", "archive": "Keats", "include full": true}' Response nameKeats's Lung slugkeats:keats-s-lung hex C8B6B0 primary sourceThe Letters, 3 February 1820 claim roleanchor Always save the slug from search results. Pass it to colour.card for reliable retrieval — slugs never break on apostrophes. 4 Tool 3 of 3 · Commercial palette analysis brand.audit Pass a palette of hex values. Returns WCAG accessibility matrix, cultural risk notes by market, archive matches with provenance, palette role assignments, and a commercial verdict. Fully deterministic — no LLM involved. curl curl -X POST https://api.colourmemory.com/brand/audit \ -H "X-Api-Key: cm demo public quickstart" \ -H "Content-Type: application/json" \ -d '{ "palette": " D4A829", " 1A5C6E", " 0F2D6B", " 0A0A0B" , "markets": "UK", "China", "Middle East" , "context": "luxury packaging" }' Response — key fields wcag matrixAll foreground/background combinations with AA/AAA pass/fail cultural riskPer-market flags with context notes commercial labelArchive-verified name for each hex verdict copyPlain-English palette verdict issuesActionable flags requiring attention 5 Optional · No code required Connect to Claude or ChatGPT All tools load instantly via MCP. No SDK. No boilerplate. One URL. Disconnect and reconnect after any update to refresh the tool list. ✗Searching for colour by hue with archive.search. Use query.hex or query.conceptual instead. archive.search is text matching, not perceptual matching. ✗Ignoring claim role. Anything marked reject is a stub with no primary source. Don't use it in client-facing work. ✗Using names instead of slugs. Get the slug from archive.search. Names break on apostrophes. Slugs always work. ✗Presenting a RacingSilks entry as Georgian evidence. Run cultural.anachronism first. A 2011 Jockey Club registration is not Georgian provenance. ✗Ignoring do not say fields. They exist to stop your agent making claims the archive doesn't support. Read them. ? Transparency What runs without an LLM? Most core endpoints are fully deterministic. Some endpoints optionally call an LLM for written output, and those are labelled clearly in the docs. Deterministic no LLM Nearest-colour matching CIEDE2000 Lab / LCh metrics and LRV WCAG contrast and accessibility matrix Palette role assignment Cultural risk scoring Archive audit and coverage gap Image palette extraction Design token export Uses LLM opt-in Brand reports and editorial briefs session.brief forensic narrative colour.hooks and colour.story agent.brief for image generation ↯ Honest caveats Limitations ·Hex values are computational approximations derived from material descriptions and historical references, not spectrophotometric measurements. ·A nearest archive match means perceptual similarity by CIEDE2000, not historical identity. Song Gold Sycee is the closest named colour — not proof the specific hex existed in 960 AD. ·Cultural risk is context-dependent and should not be treated as universal truth. Market flags are starting points for research, not final verdicts. ·Image extraction uses dominant pixel clustering. It does not yet reliably separate logo, text, product material, and background colours. ·Some endpoints generate editorial copy using an LLM. These are labelled in the docs. The underlying archive data is the same either way.