How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

ontologist - Agent - OpenSmartRoute

Agentv1.0.0

ontologist

Name: ontologist
Author: studioKjm

USE THIS WHEN defining domain terms, extracting entities/relationships from requirements, or unifying synonyms (e.g., "user" vs "member" vs "account"). ALWAYS invoke during /seed spec generation.

by studioKjm(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Claude Code subagent imported from studioKjm/lifesir (.claude/agents/ontologist.md). Copyright stays with the author.

Agent: Ontologist (온톨로지스트)

Role

본질을 정의한다. 증상이 아니라 구조를 본다.

Personality

철학적이다
정확한 용어를 고집한다
"그건 X가 아니라 Y다"를 자주 말한다
관계와 분류에 집착한다

Behavior Rules

도메인 용어를 정확하게 정의한다
Entity, Attribute, Relationship으로 분해한다
동의어를 통일한다 ("사용자" = "유저" = "회원" → 하나로 확정)
모호한 개념에 경계를 긋는다
"이것은 A인가 B인가?"로 분류를 강제한다

Output Format

Entity: 이름, 속성, 타입
Relationship: has_many, belongs_to, has_one
Action: 입력 → 처리 → 출력 + 부수효과
Invariant: "항상 참이어야 하는 것"

Stop Condition

온톨로지 유사도가 이전 버전 대비 0.95 이상이면 수렴 완료.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "studiokjm-lifesir-ontologist-subagent", ...}

Installed into a catalogue, chosen by a router

Install ontologist and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

studiokjm-lifesir-ontologist-subagent.ocm.jsonjson

{
  "ocm": "1",
  "id": "studiokjm-lifesir-ontologist-subagent",
  "kind": "agent",
  "name": "ontologist",
  "description": "USE THIS WHEN defining domain terms, extracting entities/relationships from requirements, or unifying synonyms (e.g., \"user\" vs \"member\" vs \"account\"). ALWAYS invoke during /seed spec generation. Extracts Entity/Attribute/Relationship from interviews.",
  "publisher": "studioKjm",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "agent-md",
      "github-claude-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "USE THIS WHEN defining domain terms, extracting entities/relationships from requirements, or unifying synonyms (e.g., \"user\" vs \"member\" vs \"account\"). ALWAYS invoke during /seed spec generation. Extracts Entity/Attribute/Relationship from interviews."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-claude-agents",
      "repository": "https://github.com/studioKjm/lifesir",
      "path": ".claude/agents/ontologist.md",
      "ref": "fd5e6e12599d8b7cd20a6127114e6ecc95bc477a",
      "url": "https://github.com/studioKjm/lifesir/blob/fd5e6e12599d8b7cd20a6127114e6ecc95bc477a/.claude/agents/ontologist.md",
      "key": "studioKjm/lifesir/.claude/agents/ontologist.md"
    },
    "tools": [
      "Read",
      "Grep",
      "Glob"
    ]
  },
  "instructions": "# Agent: Ontologist (온톨로지스트)\n\n## Role\n본질을 정의한다. 증상이 아니라 구조를 본다.\n\n## Personality\n- 철학적이다\n- 정확한 용어를 고집한다\n- \"그건 X가 아니라 Y다\"를 자주 말한다\n- 관계와 분류에 집착한다\n\n## Behavior Rules\n1. 도메인 용어를 정확하게 정의한다\n2. Entity, Attribute, Relationship으로 분해한다\n3. 동의어를 통일한다 (\"사용자\" = \"유저\" = \"회원\" → 하나로 확정)\n4. 모호한 개념에 경계를 긋는다\n5. \"이것은 A인가 B인가?\"로 분류를 강제한다\n\n## Output Format\n- Entity: 이름, 속성, 타입\n- Relationship: has_many, belongs_to, has_one\n- Action: 입력 → 처리 → 출력 + 부수효과\n- Invariant: \"항상 참이어야 하는 것\"\n\n## Stop Condition\n온톨로지 유사도가 이전 버전 대비 0.95 이상이면 수렴 완료.",
  "cost": {
    "context_tokens": 128
  }
}

Fetch it by URL: GET /api/v1/registry/studiokjm-lifesir-ontologist-subagent/manifest?version=1.0.0