Achiote

Achiote

TL;DR: Achiote — food-memory and cultural taste research product. Best for researchers and builders exploring food memory and heritage taste. Keywords: food memory research, cultural taste, heritage cuisine AI.

Achiote is a Model Context Protocol (MCP) server for research-first food-and-drink memory reconstruction. It helps a host AI turn incomplete family food or drink memories into structured clues, research plans, cited/provenance-ready findings, sensory analysis, sourcing/substitution strategy, and a minimum viable nostalgia cue before any fuller recipe handoff.

"The nostalgia lives in the maillard crust's interaction with the lactic tang — here's how to reproduce that."

Super Quick Start

From this repo:

npm ci

npm run build mkdir -p ~/.codex/skills/achiote cp skill/SKILL.md ~/.codex/skills/achiote/SKILL.md

Claude Code can use the checked-in .mcp.json after the build step. For Codex, add the MCP server to ~/.codex/config.toml with an absolute path to this repo's built dist/index.js:

pwd

copy the printed path and append /dist/index.js

[mcp_servers.achiote]

command = "node" args = ["/absolute/path/to/achiote/dist/index.js"] enabled = true startup_timeout_sec = 10

Restart the host AI session, then test with:

Use the achiote skill.

My mom said my Puerto Rican grandma made something that sounded like pass-teh-lay. I don't speak Spanish. Maybe plantains or pork?

Expected behavior: the host AI should use the MCP tools to collect the memory, plan research, build a dossier, and present a minimum viable nostalgia cue first. Only after that should it ask whether the user wants something more complex, such as sourcing help or a full recipe handoff.

Public Web Surfaces

The hosted/static product surface lives under docs/landing/. The core app and launch pages are dependency-free static assets served by the optional HTTP server:

• / -> docs/landing/index.html, the public landing page.
• /app -> docs/landing/app.html, the interactive food-memory detective.
• /pricing, /about, /roadmap, /changelog, /status, /blog, and /receipt -> standalone launch/trust/growth pages.
• /ai-search, /llms.txt, /privacy, /terms, /safety, /support, /compare, /robots.txt, and /sitemap.xml -> AI-search, legal, support, comparison, and crawler surfaces.

Open the HTML files directly in a browser for static review; the full route behavior is covered by npm run package:smoke.

What It Does Today

Achiote is a research-first food-and-drink memory reconstruction server. It provides 19 MCP tools that let a host AI chat client run the workflow from a fragment to a minimum viable nostalgia cue, with optional sourcing/substitution and recipe handoff if the user wants more:

All tools return MCP structuredContent. Most tools also display JSON text; intake tools may display a short human-readable summary so Claude Code output stays readable while structured data remains available to the host.

End-to-end flow

food memory fragment

-> collect_food_memory -> plan_dish_research -> optional host research / family clarification -> build_research_record / validate_research_record / extract_research_findings -> build_reconstruction_dossier -> generate_family_followup_questions -> generate_minimum_viable_nostalgia # first concrete food output -> optional analyze_nostalgic_dish / find_sensory_substitutes / source_ingredients -> optional generate_recipe # only if the user wants more

This executes through the full MCP workflow and is covered by tests/reconstruction-flow-e2e.test.ts. The preferred stopping point is the minimum viable nostalgia cue: the smallest, most accessible, easiest-to-find aroma, bite, sip, condiment, or ritual that tests whether the memory is on the right track. If the user asks for more, the MCP server can then provide sourcing/substitution context and a recipe-generation handoff. The host AI writes final recipe prose because live research, family confirmation, and adaptation judgment should not be faked by bundled data.

Requirements

• Node.js >=22.0.0
• npm

better-sqlite3 is a native dependency, so unsupported Node/platform combinations may need a compiler toolchain or a supported prebuild.

Installation

Achiote is published to npm.

npm install achiote

The published package ships the built dist/ output, so no build step is needed. To run from a source checkout instead:

npm ci

npm run build

Using with Claude Code or another MCP client

After building, add the stdio server to your MCP settings:

{

"mcpServers": { "achiote": { "command": "node", "args": ["/path/to/achiote/dist/index.js"] } } }

If installed as a package, the CLI binary is achiote.

HTTP server

An optional HTTP server provides a web UI and AI agent endpoint:

node dist/http-server.js

Listening on http://localhost:3000

Hosted Achiote (https://achiote.kyanitelabs.tech) does not enforce authentication: anonymous access is open and billing-issued API keys are honored (GET /health reports authEnabled: false). Self-hosted HTTP can still require keys: configure ACHIOTE_API_KEYS for /ask, /mcp, and voice upload endpoints. Setting ACHIOTE_AUTH_ENABLED=false does not by itself expose anonymous /ask or voice processing; set ACHIOTE_ALLOW_ANON_ASK=true only for local demos. Generate a self-hosted key with npm run keygen -- --tier pro --name admin; put the printed envRecord inside the ACHIOTE_API_KEYS JSON array, not the one-time raw key. Port defaults to 3000, configurable via PORT env var.

Shareable Memory Receipt links keep receipt JSON in the URL fragment (/receipt#data=...). URL fragments are not sent to the server, so possession of the link is the access boundary. Do not put private family memory text into telemetry or server-side share records.

Local OSS speech

Voice is disabled by default and uses only local OSS speech engines when configured. The recommended stack is whisper.cpp for multilingual speech-to-text and Kokoro-82M for local read-aloud. This path is aimed at immigrant families and children of immigrants: speech input defaults to auto language detection so accents, transliterated dish names, and code-switching can reach the same food-memory workflow as typed text. Exact language and accent quality depends on the local model you install.

Example environment:

ACHIOTE_STT_PROVIDER=whispercpp

ACHIOTE_WHISPER_CPP_BINARY=/usr/local/bin/whisper-cli ACHIOTE_WHISPER_CPP_MODEL=/models/ggml-large-v3-turbo.bin ACHIOTE_STT_LANGUAGE=auto ACHIOTE_STT_LANGUAGES=auto,es,hi,zh,ar,fr,pt,tl

ACHIOTE_TTS_PROVIDER=kokoro ACHIOTE_KOKORO_COMMAND='["python","/opt/kokoro/speak.py","--text","{text}","--output","{output}","--voice","{voice}","--language","{language}"]' ACHIOTE_KOKORO_VOICE='af_heart' A