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.

ml-playground-py - Skill - OpenSmartRoute

Imported from hyperswine/ml-playground-py (AGENTS.md). Install upstream with npx skills add hyperswine/ml-playground-py. Copyright stays with the author.

Working in this repository

Run categorized Python scripts through uv run --locked qos SCRIPT ...; use qos list for names and qos test for the regression suite.
Active source is under src/ml_playground/. Update configs/layout.json when adding or moving modules. .runtime/workspace is generated compatibility plumbing; edit the source files, not its links.
Keep frozen job bundles, compiler snapshots, benchmark inputs and experiment receipts unchanged. Their hashes and recorded paths are historical provenance.
Narrative documentation belongs in dated docs/YYYY-MM-DD-TOPIC.md pages, indexed by docs/README.md. Record substantive updates with an ISO-8601 time and timezone. Raw measurements belong in docs/data/; weights and prepared model datasets belong in ignored files under artifacts/.
.env and .secrets/ are local and ignored. Never print credential values or include them in bundles, logs, Git changes or training corpora. Parent AGENTS.md instructions still apply.
The M1 checkout remains /Users/jq/qos_ai_eval through Tailscale as jq. Verify the intended source/compiler identity before comparing experiments.
Retain RunPod network volume xewpn3z8za. Repository maintenance does not authorize starting paid compute, deleting retained artifacts or changing the default model.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot 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}'

Install ml-playground-py 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.

ml-playground-py

About

Working in this repository

Use it

Install ml-playground-py 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