Stargazer v3 — Technical Documentation

Architectural Overview

Stargazer v3 is a multi-platform conversational AI bot that bridges Discord and Matrix with a shared LLM inference pipeline, extensible tool-calling framework, and a neurochemical simulation engine for affective computing.

System Architecture

The system is organized into the following layers:

Entry Point & Lifecycle — main boots the BotRunner, which manages multi-platform adapter lifecycles, message routing, and the web management GUI.

Platform Adapters — The platforms package provides a PlatformAdapter interface implemented by platforms.discord and platforms.matrix. Adapters normalize incoming messages into IncomingMessage objects and expose a uniform reply API.

Message Processing Pipeline — message_processor is the core orchestrator. For each incoming message it:

Preprocesses (URL extraction, attachment handling, multimodal parts)
Resolves conversation history via conversation and message_cache
Classifies and selects relevant tools via classifiers.vector_classifier
Gathers RAG context from rag_system
Builds the LLM prompt with prompt_context and prompt_renderer
Calls the LLM via openrouter_client
Postprocesses the response with response_postprocessor

Tool Framework — tools provides the ToolRegistry decorator system. Each tool file in the tools/ directory is auto-loaded by tool_loader. Tools are async callables that receive optional ToolContext for bot-internal access. The classifiers.vector_classifier selects tools per-message via semantic embedding similarity.

Neurochemical Model (NCM) — An affective computing layer that simulates neurochemical states: