Skip to main content
Version: 1.0.0

LLM APIs

Conversational AI gateway for thread management, messaging, tool orchestration (MCP), semantic memory, and LLM proxy. (Voice sessions are in progress — not yet generally available.)

This service centralizes authentication/context derivation and bridges requests to downstream actors and services (ConversationManagerActor, ConversationActor, MCPService, MemoryService, OpenRouterService).

All endpoints use POST /api/v1/llm/gateway/<method> with a JSON request body.

See the Conversations guide for thread lifecycle, async generation, and configuration. See the MCP Tools guide for tool calling, approval flows, and client-side tools. See the Memory guide for semantic memory search and conversation integration.

Authentication

Security Scheme Type:

http

HTTP Authorization Scheme:

bearer

Bearer format:

JWT