Inference gateway

The inference gateway is Achiral's external OpenAI-compatible memory endpoint. It authenticates an organization token, verifies the request organization, adds private organization memory, calls the model layer, and can write the completed turn back into memory.

The public model id is chiro. Internal provider and registry names are intentionally hidden from clients.

Routes

Method	Path	Purpose
GET	/v1/health	Liveness check. No auth required.
GET	/v1/models	Return the public model id, chiro.
POST	/v1/chat/completions	Run a memory-augmented chat completion. Supports streaming and non-streaming responses.

Example

export ACHIRAL_MEMORY_ENDPOINT="https://domain-com.achiral.ai/v1"
export ACHIRAL_MCP_TOKEN="acm_..."

curl "$ACHIRAL_MEMORY_ENDPOINT/chat/completions" \
  -H "Authorization: Bearer $ACHIRAL_MCP_TOKEN" \
  -H "Content-Type: application/json" \
  -H "x-achiral-memory: auto" \
  -d '{
    "model": "chiro",
    "messages": [
      {"role": "user", "content": "What changed in our onboarding workflow this week?"}
    ],
    "temperature": 0.2,
    "max_tokens": 600
  }'

Use Memory API for the full surface map.