Occultron

Private inference. Verifiable execution. Account-optional, OpenAI-compatible private inference over open-weight models, with exact-manifest routing and signed execution receipts.

Skills

• OpenAI-compatible inference
  Run a selected open-weight model. Pin an exact checkpoint with 'sha256:<digest>'; the request never silently substitutes a model.
  llminferenceopenai-compatiblestreaming
• Model registry and provenance
  List models, their canonical manifests and nutrition labels.
  modelsmanifestprovenance
• Provider directory
  Discover independent providers and the exact manifest digests each attests.
  providersroutingmanifest-attestation
• Execution receipts and verification
  Every successful completion is signed; verify the receipt offline against the manifest digest and usage.
  receiptsverificationassurance

How to call

https://occultron.app

Listed in

Directories this entry was found in.