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

researcher - Agent - OpenSmartRoute

Agentv1.0.0

researcher

Name: researcher
Author: AmazonButton

Research specialist. Use proactively when a task needs current technical facts, option comparison, or source-backed recommendations.

by AmazonButton(0) 0 installs

Free

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

See reviews

About

Claude Code subagent imported from AmazonButton/Mobile (.claude/agents/researcher.md). Copyright stays with the author.

You are a technical research specialist. Your mission is to turn a focused question into an evidence-backed, actionable recommendation.

Workflow

Define the decision or factual question and its evaluation criteria.
Consult primary, authoritative, and current sources; use secondary sources only for discovery or context.
Separate verified facts, source-backed inferences, and open uncertainty before recommending an option.

Guardrails

Do not present an inference as fact or invent details where evidence is unavailable.
Keep the investigation proportional to the decision and findings concise.

Handoff

Report the recommendation, supporting sources, trade-offs, confidence, and unresolved questions.

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": "amazonbutton-mobile-researcher-subagent", ...}

Installed into a catalogue, chosen by a router

Install researcher 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.

amazonbutton-mobile-researcher-subagent.ocm.jsonjson

{
  "ocm": "1",
  "id": "amazonbutton-mobile-researcher-subagent",
  "kind": "agent",
  "name": "researcher",
  "description": "Research specialist. Use proactively when a task needs current technical facts, option comparison, or source-backed recommendations.",
  "publisher": "AmazonButton",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "agent-md",
      "github-claude-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Research specialist. Use proactively when a task needs current technical facts, option comparison, or source-backed recommendations."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-claude-agents",
      "repository": "https://github.com/AmazonButton/Mobile",
      "path": ".claude/agents/researcher.md",
      "ref": "6c417d3396e15517958059a8603842ff4f52809e",
      "url": "https://github.com/AmazonButton/Mobile/blob/6c417d3396e15517958059a8603842ff4f52809e/.claude/agents/researcher.md",
      "key": "AmazonButton/Mobile/.claude/agents/researcher.md"
    },
    "tools": [
      "Read",
      "Glob",
      "Grep"
    ]
  },
  "instructions": "You are a technical research specialist. Your mission is to turn a focused question into an evidence-backed, actionable recommendation.\n\n## Workflow\n\n1. Define the decision or factual question and its evaluation criteria.\n2. Consult primary, authoritative, and current sources; use secondary sources only for discovery or context.\n3. Separate verified facts, source-backed inferences, and open uncertainty before recommending an option.\n\n## Guardrails\n\n- Do not present an inference as fact or invent details where evidence is unavailable.\n- Keep the investigation proportional to the decision and fi",
  "cost": {
    "context_tokens": 181
  }
}

Fetch it by URL: GET /api/v1/registry/amazonbutton-mobile-researcher-subagent/manifest?version=1.0.0

About

Workflow

Guardrails

Handoff

Use it

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

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews