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.

magi-knowledge - Skill - OpenSmartRoute

Imported from dogmaai/magi-knowledge (AGENTS.md). Install upstream with npx skills add dogmaai/magi-knowledge. Copyright stays with the author.

Agent instructions

Read index.md, README.md and COLLABORATION.md before changing this bundle. Then read the relevant documents under system/ or _lilith_safe/.

This repository is the shared specification. The old magi-stg specification is archived; exports and Cloudflare mirrors are derived.
Check open Issues/PRs before starting. Use one implementation owner and preserve the existing branch on handoff or review fixes.
Preserve the LILITH contamination boundary. Never copy full-system knowledge or development instructions into _lilith_safe/.
Concept Markdown requires a non-empty type frontmatter field. system/ concepts use lilith_safe: false; training concepts use lilith_safe: true. Follow the reserved-file rules in okf_common.py.
Compare disputed values against the implementation and record the source revision. If access is blocked, report it; do not guess current defaults, deployed settings or the resolution of a policy conflict.
Sensitive changes require independent review as listed in COLLABORATION.md. Repository-specific deployment rules continue to apply; this document grants no production-operation authority.
Update the relevant concept documents and log.md for approved changes. Regenerate exports rather than editing generated copies.

Run the existing gates from the repository root:

python scripts/okf_lint.py
python scripts/test_lilith_safe_loader.py

Report the actual results in the PR, using Summary, Key Changes and Verification. Stop acknowledgement loops once agreement is reached.

Install magi-knowledge 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.

magi-knowledge

About

Agent instructions

Install magi-knowledge 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

Use it

Manifest

Reviews