
**Pick the right LLM for any task.** XFMS infers which quality in its catalog against those dimensions, and returns a ranked shortlist with plain-English rationale per pick. The catalog updates continuously from **8 independent third-party evaluators** — no provider self-reports, no single-source benchmarks. Missing data is recorded as missing, not interpolated. **Three tools:** - `rank` — ranked shortlist with weights and rationale - `pick` — single best pick - `discover` — which quality dimensions matter, without ranking **No OpenRouter key needed.** The hosted endpoint covers inference; you only need a free XFMS access token from [xpansion .dev/xfms/get-started](https://xpansion.dev/xfms/get-started). Part of the [Xpansion Framework](https://xpansion.dev) — an enforcement layer for AI-assisted work.
First seen 2 Oct 2026. One server, whatever directories list it: each directory listing keeps its own page and history.
Tools
No tool list captured yet.
| Directory | Listing | Tier | First seen |
|---|---|---|---|
| Smithery | XFMS - Xpansion Framework Model Source | - | 2 Oct 2026 |