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

setup-plugins - Prompt - OpenSmartRoute

Promptv1.0.0

setup-plugins

Name: setup-plugins
Author: Palo-IT-GitHub-Demos

Install delivery, implementation-plan, and architecture-reviewer plugins from the gen-e2 marketplace.

by Palo-IT-GitHub-Demos(0) 0 installs

Free

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

See reviews

About

Prompt file imported from Palo-IT-GitHub-Demos/model-compass (.github/prompts/setup-plugins.prompt.md). Copyright stays with the author.

Install the following gen-e2 plugins into this project using the lab-registry MCP server:

delivery (v0.2.3) — story-to-PR delivery workflow
implementation-plan (v0.1.0) — deterministic, AI-executable implementation plans
architecture-reviewer (v0.1.0) — evidence-first architecture analysis + Mermaid diagrams

For each plugin:

Fetch the full install package from the registry via mcp_lab-registry_get_plugin_install_package
Write all skill files to .github/skills/<name>/SKILL.md (Copilot) and .claude/skills/<name>/SKILL.md (Claude Code)
Write all agent files to .github/agents/<name>.agent.md (Copilot) and .claude/agents/<name>.md (Claude Code)
Ensure .claude/plugins/<plugin>/plugin.json is up to date

After installation, list all installed artefacts grouped by plugin.

Use it

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

Install the following gen-e2 plugins into this project using the lab-registry MCP server:

1. `delivery` (v0.2.3) — story-to-PR delivery workflow
2. `implementation-plan` (v0.1.0) — deterministic, AI-executable implementation plans
3. `architecture-reviewer` (v0.1.0) — evidence-first architecture analysis + Mermaid diagrams

For each plugin:
- Fetch the full install package from the registry via `mcp_lab-registry_get_plugin_install_package`
- Write all skill files to `.github/skills/<name>/SKILL.md` (Copilot) and `.claude/skills/<name>/SKILL.md` (Claude Code)
- Write all agent files to `.github/agents/<name>.agent.md` (Copilot) and `.claude/agents/<name>.md` (Claude Code)
- Ensure `.claude/plugins/<plugin>/plugin.json` is up to date

After installation, list all installed artefacts grouped by plugin.

Installed into a catalogue, chosen by a router

Install setup-plugins 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.

palo-it-github-demos-model-compass-setup-plugins-prompt.prompt.jsonjson

{
  "prompt": "Install the following gen-e2 plugins into this project using the lab-registry MCP server:\n\n1. `delivery` (v0.2.3) — story-to-PR delivery workflow\n2. `implementation-plan` (v0.1.0) — deterministic, AI-executable implementation plans\n3. `architecture-reviewer` (v0.1.0) — evidence-first architecture analysis + Mermaid diagrams\n\nFor each plugin:\n- Fetch the full install package from the registry via `mcp_lab-registry_get_plugin_install_package`\n- Write all skill files to `.github/skills/<name>/SKILL.md` (Copilot) and `.claude/skills/<name>/SKILL.md` (Claude Code)\n- Write all agent files to `.github/agents/<name>.agent.md` (Copilot) and `.claude/agents/<name>.md` (Claude Code)\n- Ensure `.claude/plugins/<plugin>/plugin.json` is up to date\n\nAfter installation, list all installed artefacts grouped by plugin.",
  "variables": [],
  "notes": "Install delivery, implementation-plan, and architecture-reviewer plugins from the gen-e2 marketplace. Mode: agent.",
  "metadata": {
    "source": {
      "provider": "github-prompts",
      "repository": "https://github.com/Palo-IT-GitHub-Demos/model-compass",
      "path": ".github/prompts/setup-plugins.prompt.md",
      "ref": "415058a3efc3aa48c03e3b32b1bd0ffb7f97543c",
      "url": "https://github.com/Palo-IT-GitHub-Demos/model-compass/blob/415058a3efc3aa48c03e3b32b1bd0ffb7f97543c/.github/prompts/setup-plugins.prompt.md",
      "key": "Palo-IT-GitHub-Demos/model-compass/.github/prompts/setup-plugins.prompt.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/palo-it-github-demos-model-compass-setup-plugins-prompt/manifest?version=1.0.0

About

Use it

Install setup-plugins 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