Engine pairing
Companion ships no model. You decide what’s behind the chat window — and you can change your mind any Tuesday.
Pairing is how Companion learns where to send inference. You can pair several engines at once; each keeps its own catalog entry and you route per message.
Add an engine
Section titled “Add an engine”Settings → Infrastructure → Engine → Add.
| You have | Endpoint to add |
|---|---|
| OdyssAI-X cluster | http://<server>:8000 |
| Telemak Mac | http://<telemak-ip>:8003 |
| Ollama / LM Studio / vLLM | their local OpenAI endpoint |
| A cloud key | Add Cloud Provider → OpenRouter / Anthropic / OpenAI |
Click Test endpoint. Companion fetches the capability contract, learns the per-model capabilities, and merges the models into the unified catalog.
The three rails
Section titled “The three rails”How Companion actually reaches a model. The default is the first one; the others exist for compatibility.
| Rail | What it does | When |
|---|---|---|
| Gateway (default) | Talks directly to OdyssAI-X / Telemak over their native OpenAI + Anthropic surface. Capabilities from the contract, inference from the engine. | The normal path. Local clusters and Telemak. |
| Hybrid | Capabilities from the engine contract, inference proxied through LiteLLM. | Rare — only when a third-party rail needs it. |
| Legacy | Everything through LiteLLM. | Compatibility fallback only. |
The gateway is the rail. OdyssAI-X is the inference path; LiteLLM is a legacy fallback, not the centre. If a screen or doc frames LiteLLM as central, it’s stale — pair to the engine directly and stay on the gateway.
Multiple engines, one catalog
Section titled “Multiple engines, one catalog”Pair a cluster and a Telemak and a cloud key, and the model picker shows all of them with the engine each model belongs to. Route per message: a cheap local model for drafts, a frontier cloud model for a hard problem, a Telemak coder for code — same conversation, same history, same memory.
What pairing does not move
Section titled “What pairing does not move”Pairing changes where inference runs, nothing else. Your conversations, memory and projects live in Companion’s Postgres regardless of which engine answers. Switch from a local cluster to a cloud key and back without migrating a single byte of history.
Read next
Section titled “Read next”- The capability contract — what pairing reads.
- Model picker — choosing among the paired engines.
- Getting started — the first pairing, step by step.