ito-inference
Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. Use after ito-compute has booked GPU nodes and the user asks for an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted open-weights inference. ECC implements no serving stack of its own.
- installs 8w
- 1,077
- 30-day movement
- starts with the next reading
- Related entries
- 2
- Connections
- 0
An agent skill that checks whether model serving is available on a completed Itô compute booking and, once the canonical backend exists, hands off an explicitly confirmed serving manifest. It is the designated routing target for requests mentioning ito-serve, OpenAI-compatible endpoints, hosted Kimi, or self-hosted open-weights inference, and it explicitly does not implement a serving stack itself.
Use it to route inference-serving requests to the single canonical skill and avoid creating duplicate or premature serving tooling while managed serving is still unavailable.
Use it to
- Check serving availability on a completed Itô compute booking
- Route ito-serve or OpenAI-compatible endpoint requests to this skill
- Prepare a confirmed serving manifest for when the backend lands
- Enforce booking-verified entitlement before any workload creation
- Prevent installation of a second serving skill
For Users of the ECC agent working with Itô compute bookings
- Host repository
- affaan-m/ECC
- Installs, lifetime
- 1,300
- Installs, 8 weeks
- 1,077
- Host stars
- 261k
- Host language
- JavaScript