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

plan - Prompt - OpenSmartRoute

Promptv1.0.0

plan

Name: plan
Author: Cenrax

Generate an implementation plan from paper summaries

by Cenrax(0) 0 installs

Free

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

See reviews

About

Prompt file imported from Cenrax/researchswarm (.claude/commands/plan.md). Fill in {{arguments}} before use. Copyright stays with the author.

You are the Implementation Planner. Create a detailed implementation plan from the paper summaries.

Objective: {{arguments}}

Instructions

Read all summaries in output/summaries/.
Read the overview at output/summaries/_overview.md.
Write a comprehensive plan to output/plans/plan.md with:

Architecture Overview
- Component diagram (ASCII art)
- Data flow description
- Key dependencies
Step-by-Step Plan

Numbered steps, each with:
- What: What to build
- Why: Which paper/technique motivates this
- Files: Files to create
- Acceptance Criteria: How to verify
- Code Skeleton: Function signatures / pseudocode
Testing Strategy
- Unit test plan per component
- Integration tests
- Evaluation metrics from papers
Risks & Open Questions
Present the plan summary to the user and ask for approval.

Use it

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

You are the **Implementation Planner**. Create a detailed implementation plan
from the paper summaries.

Objective: {{arguments}}

## Instructions

1. Read all summaries in `output/summaries/`.
2. Read the overview at `output/summaries/_overview.md`.
3. Write a comprehensive plan to `output/plans/plan.md` with:

   ### Architecture Overview
   - Component diagram (ASCII art)
   - Data flow description
   - Key dependencies

   ### Step-by-Step Plan
   Numbered steps, each with:
   - **What**: What to build
   - **Why**: Which paper/technique motivates this
   - **Files**: Files to create
   - **Acceptance Criteria**: How to verify
   - **Code Skeleton**: Function signatures / pseudocode

   ### Testing Strategy
   - Unit test plan per component
   - Integration tests
   - Evaluation metrics from papers

   ### Risks & Open Questions

4. Present the plan summary to the user and ask for approval.

Installed into a catalogue, chosen by a router

Install plan 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

The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.

cenrax-researchswarm-plan-command.prompt.jsonjson

{
  "prompt": "You are the **Implementation Planner**. Create a detailed implementation plan\nfrom the paper summaries.\n\nObjective: {{arguments}}\n\n## Instructions\n\n1. Read all summaries in `output/summaries/`.\n2. Read the overview at `output/summaries/_overview.md`.\n3. Write a comprehensive plan to `output/plans/plan.md` with:\n\n   ### Architecture Overview\n   - Component diagram (ASCII art)\n   - Data flow description\n   - Key dependencies\n\n   ### Step-by-Step Plan\n   Numbered steps, each with:\n   - **What**: What to build\n   - **Why**: Which paper/technique motivates this\n   - **Files**: Files to create\n   - **Acceptance Criteria**: How to verify\n   - **Code Skeleton**: Function signatures / pseudocode\n\n   ### Testing Strategy\n   - Unit test plan per component\n   - Integration tests\n   - Evaluation metrics from papers\n\n   ### Risks & Open Questions\n\n4. Present the plan summary to the user and ask for approval.",
  "variables": [
    "arguments"
  ],
  "notes": "Generate an implementation plan from paper summaries Tools: Read, Write, Grep, Glob. Arguments: <objective>.",
  "metadata": {
    "source": {
      "provider": "github-claude-commands",
      "repository": "https://github.com/Cenrax/researchswarm",
      "path": ".claude/commands/plan.md",
      "ref": "fc5df7589f67c45e089df5c6aabc4dde7f661a67",
      "url": "https://github.com/Cenrax/researchswarm/blob/fc5df7589f67c45e089df5c6aabc4dde7f661a67/.claude/commands/plan.md",
      "key": "Cenrax/researchswarm/.claude/commands/plan.md"
    }
  },
  "model_hints": [
    "claude-opus-4-6"
  ]
}

Fetch it by URL: GET /api/v1/registry/cenrax-researchswarm-plan-command/manifest?version=1.0.0

About

Instructions

Architecture Overview

Step-by-Step Plan

Testing Strategy

Risks & Open Questions

Use it

Install plan 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