# Occultron

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

- **Domain**: `occultron.app`
- **Provider**: Occultron (https://occultron.app)
- **A2A protocol version**: 0.3.0
- **Kind**: a2a_agent
- **Live-responds (last probe)**: False
- **Signed card**: False
- **Streaming**: True
- **Quality score**: 78%

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

## URLs
- Agent card: https://occultron.app/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/occultron.app