edition-api

EDITION Intelligence Platform

Japan Knowledge Gateway for autonomous AI agents.

20 knowledge domains · 43 MCP tools · 7 Skills Packs · 100+ REST endpoints Verified ground truth for operating in the Japanese market. Quality score: 97.8/100.

Production API: api.edition.sh — Free beta, no registration required.

Interactive Demo: Tourist Agent Demo — Watch 6 domains work together in real-time.

---

Why EDITION?

AI agents working in Japan hit walls that generic LLMs can't solve:

Challenge	What goes wrong
Keigo (敬語)	「お持ちすれば喜ばれるかと存じます」 — hidden subject, layered honorifics, uncertainty expression. Generic NLP treats this as noise.
Implicit agreements	Japanese business communication rarely states things directly. Agents need cultural decoding.
Regulatory maze	10+ industries with overlapping national/prefectural regulations, most documentation only in Japanese.
Procedural complexity	Company incorporation, visa, banking — each requires 5-8 steps with specific documents, deadlines, and costs.

EDITION provides verified, structured intelligence that agents can use as ground truth instead of hallucinating cultural nuances, legal requirements, and procedural details.

---

20 Knowledge Domains

#	Domain	Tools	What it covers
1	Memory	memory_store memory_recall memory_facts memory_context memory_extract	Three-layer persistent memory (Episode/Fact/Context) with Japanese keigo analysis and social hierarchy detection
2	Regulation	regulation_check regulation_industries regulation_tourist	10 industries (food, real estate, finance, healthcare, construction, education, transport, retail, IT, manufacturing) + tourist compliance
3	Protocol	protocol_check protocol_list	Nemawashi, ringi, hourensou, meishi koukan, sekijun, zoutou — step-by-step procedures with cultural context
4	Calendar	calendar_check calendar_list	Fiscal year (April start), Golden Week, Obon, year-end, gift seasons, administrative deadlines
5	Regional	regional_check regional_list	Tokyo vs Osaka negotiation styles, local subsidies, prefectural regulations, dialect considerations
6	Organization	organization_check organization_list	Keiretsu networks, corporate hierarchy (bucho/kacho), payment customs (net-60), contract practices
7	Foreign Entry	foreign_entry_check foreign_entry_list	6 categories: company incorporation (KK/GK), management visa, bank account, real estate, tax registration, employee hiring
8	Travel	travel_search travel_list	Shinkansen, IC cards, ryokan etiquette, onsen rules, restaurant ordering, tipping customs
9	Entertainment	entertainment_search entertainment_list	Oshi-katsu fan culture, anime pilgrimage, live event manners, seasonal festivals
10	Daily Life	daily_life_search daily_life_list	Postal/address systems, garbage sorting by municipality, utilities (electricity/gas/water/NHK), healthcare navigation
11	Language	language_search language_list	Keigo honorific system, counter words (josushi), name/address structure, business Japanese templates
12	Food Culture	food_search food_list	Dining etiquette, cuisine classification, restaurant navigation (shokkenki, izakaya, sushi counter), dietary restrictions (halal, vegetarian, allergies)
13	Disaster & Safety	disaster_search disaster_list	Earthquake shindo scale & EEW, typhoon warning levels, emergency contacts (110/119/118), preparedness checklists
14	Healthcare	healthcare_search healthcare_list	National health insurance, hospital navigation, prescription system, medical Japanese terminology
15	Education	education_search education_list	School system (6-3-3-4), entrance exams, international schools, university admission for foreigners
16	Real Estate	real_estate_search real_estate_list	Rental process (shikikin/reikin/hoshoukin), property types, foreigner-friendly agencies, contract terms
17	Tax	tax_search tax_list	Income tax, consumption tax, withholding, year-end adjustment, tax filing for foreigners and businesses
18	Banking & Finance	banking_search banking_list	Bank account types, remittance, fintech services, corporate banking, payment systems
19	Visa & Immigration	visa_search visa_list	Visa categories, status of residence, renewal procedures, permanent residency, naturalization
20	Cross-Domain	search	Search all 20 domains simultaneously with a single query

---

Skills Packs (MCP Skills Primitive)

Pre-built knowledge packs that bundle domain expertise, SOPs, and tool orchestration instructions. Skills-aware agents can load these to gain structured Japan operational knowledge.

Skill Pack	Domains	Use Case
japan-market-entry	regulation, foreign_entry, organization	Company incorporation, visa, banking
japan-business-ops	protocol, calendar, regional, language	Meetings, nemawashi, business Japanese
japan-travel-guide	travel, food, entertainment, disaster	Tourist assistance, dining, safety
japan-daily-living	daily_life, food, language	Utilities, garbage, healthcare
japan-cultural-context	protocol, organization, language	Implicit communication, hierarchy
japan-safety-compliance	disaster, regulation	Earthquake response, regulatory compliance
japan-governance-compliance	regulation, governance	Audit trails, compliance reporting, AI Act readiness

→ Full Skills Pack documentation

---

Governance Intelligence

EDITION includes built-in compliance audit trail tools for agents operating under governance requirements. Available in both Progressive Discovery and Legacy modes.

regulation_check → compliance_log → compliance_report
      ↓                   ↓                  ↓
  Check rules      Record audit       Generate report

Tool	Purpose
compliance_log	Create immutable, timestamped audit record after any regulatory check
compliance_report	Generate governance reports (summary / detailed / JSON) from audit trail

Designed for EU AI Act (Aug 2026) and upcoming Japan AI governance compliance.

---

Quick Start

Option 1: npx (Recommended for Claude Desktop / Cursor)

npx -y edition-mcp-server

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "edition": {
      "command": "npx",
      "args": ["-y", "edition-mcp-server"],
      "env": {
        "EDITION_API_URL": "https://api.edition.sh",
        "EDITION_API_KEY": "edition_dev_key_for_testing"
      }
    }
  }
}

Option 2: Smithery

npx -y smithery mcp add hiroshi-c9/edition

Option 3: REST API (Direct)

# Cross-domain search
curl -X POST https://api.edition.sh/api/v1/search \
  -H "Content-Type: application/json" \
  -d '{"query": "How do I start a tech company in Tokyo?"}'

# Regulation check
curl -X POST https://api.edition.sh/api/v1/regulation/check \
  -d '{"action": "open restaurant", "industry": "food_service"}'

# Business protocol
curl -X POST https://api.edition.sh/api/v1/protocol/check \
  -d '{"query": "nemawashi consensus building"}'

---

Memory API — Japanese-aware Persistent Memory

Store episodes, auto-extract structured facts with keigo analysis, social hierarchy detection, and confidence scoring.

Input:  "佐藤部長にはワインをお持ちすれば喜ばれるかと存じます"

Output:
  Subject:    佐藤 (役職: 部長)
  Predicate:  好む
  Object:     ワイン
  Keigo:      Level 2 (尊敬語)
  Hierarchy:  superior
  Confidence: 0.7 (推測 — not stated as fact)
  Tense:      present

Three-layer architecture:

• Episodes — raw conversation logs
• Facts — structured knowledge (subject→predicate→object triples)
• Context — aggregated session summaries per entity/topic

MCP Capabilities

Category	Count	Details
Tools	43	All with annotations (readOnlyHint, destructiveHint, idempotentHint)
Resources	2	edition://domains (domain catalog), edition://quality (trust scores)
Prompts	2	japan_business_briefing (by industry), japan_travel_guide (by destination)

API Endpoints

Memory

Method	Endpoint	Description
POST	/api/v1/memory/episodes	Store episode (auto_extract=true for auto fact extraction)
POST	/api/v1/memory/recall	Semantic search across episodes
GET	/api/v1/memory/facts	List structured facts
GET	/api/v1/memory/context	Session context summary
POST	/api/v1/memory/extract	Extract facts from text (store=true to persist)

Regulation & Compliance

Method	Endpoint	Description
POST	/api/v1/regulation/check	Check regulations (10 industries + tourist)
GET	/api/v1/regulation/industries	List all regulated industries
GET	/api/v1/regulation/tourist	Tourist regulation categories

Business Intelligence

Method	Endpoint	Description
POST	/api/v1/protocol/check	Search business protocols
GET	/api/v1/protocol/list	List all protocols
POST	/api/v1/calendar/check	Search business calendar
GET	/api/v1/calendar/list	List calendar categories
POST	/api/v1/regional/check	Search regional differences
GET	/api/v1/regional/list	List regional categories
POST	/api/v1/organization/check	Search organizational structures
GET	/api/v1/organization/list	List organization categories

Market Entry

Method	Endpoint	Description
POST	/api/v1/foreign-entry/check	Foreign market entry guides
GET	/api/v1/foreign-entry/list	List entry categories (6 total)

Lifestyle & Culture

Method	Endpoint	Description
POST	/api/v1/travel/search	Travel intelligence
POST	/api/v1/entertainment/search	Entertainment & pop culture
POST	/api/v1/daily-life/search	Daily life knowledge
POST	/api/v1/language/search	Japanese language
POST	/api/v1/food/search	Food culture
POST	/api/v1/disaster/search	Disaster & safety
POST	/api/v1/healthcare/search	Healthcare system
POST	/api/v1/education/search	Education system
POST	/api/v1/real-estate/search	Real estate
POST	/api/v1/tax/search	Tax system
POST	/api/v1/banking/search	Banking & finance
POST	/api/v1/visa/search	Visa & immigration

Cross-Domain

Method	Endpoint	Description
POST	/api/v1/search	Search all 20 domains simultaneously

---

Data Quality

All knowledge entries include:

• source_url — Link to authoritative source (government websites, official organizations)
• last_verified — Date of last verification
• confidence — Verification status (verified / estimated)
• version — Entry version with changelog

Sources include: 厚生労働省 (MHLW), 国税庁 (NTA), 法務省 (MOJ), 国土交通省 (MLIT), 経済産業省 (METI), 日本経団連 (Keidanren), JETRO, 入管庁 (ISA).

Tech Stack

Layer	Technology
API	FastAPI (Python)
Memory Store	SQLite + ChromaDB (vector search)
MCP Server	TypeScript (MCP SDK v1.12+)
LLM	Gemini / Claude / GPT (fact extraction)
Hosting	Render (api.edition.sh)

Agent Discovery

Protocol	Endpoint
MCP (Streamable HTTP)	POST https://api.edition.sh/mcp
A2A Agent Card	GET https://api.edition.sh/.well-known/agent.json
MCP Server Card	GET https://api.edition.sh/.well-known/mcp/server-card.json
OpenAPI / Swagger	GET https://api.edition.sh/docs

Agent Harness Compatible

EDITION is designed as a Tool Registry / Japan Knowledge Layer for agent harnesses. All 43 tools include MCP annotations (readOnlyHint, destructiveHint, idempotentHint), usage guidelines, and behavioral transparency metadata — enabling harness frameworks to auto-discover, evaluate, and integrate EDITION tools without manual configuration.

Freemium Access

Tier	Domains	Rate Limit	Price
Free	8 core domains	100 req/day	Free
Pro	All 20 domains (incl. tax, banking, healthcare, visa)	10,000 req/day	¥2,980/mo
Enterprise	All domains + priority support	Unlimited	Contact

Anonymous access defaults to Free tier. Register for an API key at POST /api/v1/auth/register.

Registries

Registry	Status
npm	✅ Published (v0.4.0)
Smithery	✅ Listed (43 tools)
Glama	✅ Grade A Coherence

Why Not Mem0 / Letta / Zep?

Those are excellent general-purpose memory tools. But they don't:

• Parse Japanese keigo levels (丁寧語 / 尊敬語 / 謙譲語)
• Detect implicit social hierarchy from honorific patterns
• Score confidence based on Japanese speech patterns (断定 vs 推測 vs 伝聞)
• Include a Japanese regulatory database with 20 knowledge domains

Japanese business context is structurally different. Agents need purpose-built infrastructure to navigate it.

License

MIT