SOUND
LANGUAGE
THEME

Hi, I'm Lyra, this portfolio's AI assistant. Click to ask me about the projects, the stack, or Ever's background.

Autonomous AI Agents | Microkernel + Hexagonal | CQRS Status: In development

AETHELGARD

System of autonomous conversational AI agents in testing phase: a persuasive and empathetic sales agent, and a document reader with verified responses. Hybrid adaptable architecture.

Pure software architecture

Robust backend · No visual UI

Project Overview

Autonomous conversational agents. Problem: keeping agents adaptable without touching code. Solution: Microkernel + Hexagonal + CQRS, personalities loaded from YAML. Stack: Python, FastAPI, Google ADK, ChromaDB, pgvector. Result: sales agent with vector memory, document agent with zero hallucinations.

RoleAI Systems Architect & Backend Engineer
ClientInternal R&D project for commercial and document automation
DurationApril 2026 - May 2026
Year2026

Core Modules

Microkernel Core & Agent Orchestrator

The system core is minimal: it only handles agent registration (plugins) and communication between them. A central orchestrator classifies the user's intent and routes the conversation to the appropriate specialized agent (sales or documents) without core intervention, allowing agents to be added or removed on the fly.

Sales Agent with Dynamic Personalities

Autonomous agent that adopts different personalities (aggressive, consultive, empathetic seller) based on the client's profile. Sales strategies (SPIN Selling, Challenger, etc.) are loaded from YAML files. Includes semantic product search tools in ChromaDB and long-term vectorized memory (Gemini Embeddings).

Document Agent with Extreme RAG

Specialized agent for processing long documents (manuals, contracts, regulations). Uses ChromaDB and pgvector for semantic vector search, with intelligent chunking (recursive or entity-based). Responds exclusively with citations extracted from the documents, with zero hallucinations.

Hexagonal Architecture + CQRS

Ports and adapters isolate business logic from infrastructure details (AI models, databases, APIs). CQRS separates write operations (commands) from read operations (queries), allowing each side to scale independently and use different optimizations (cache, vector indexes).

Vectorized Long-Term Memory

Stores preferences, conversation history, and relevant user data as vectors in ChromaDB (Gemini Embedding 2). The sales agent can retrieve information from previous interactions to personalize offers without requiring explicit login.

Response Quality Supervisor

Safety filter that reviews every generated response before sending it to the user. Validates that there are no fabricated facts, the tone is appropriate, and business rules are respected. If issues are detected, it corrects or replaces the response with a controlled fallback message.

Persistent Multi-Instance Sessions

Conversations are stored in PostgreSQL (adk_sessions and adk_events tables), allowing the full history to survive server restarts and be shared across multiple server instances. The agent remembers context (size, preferences, mentioned products) even if the user returns days later.

Technologies Implemented

frontend

Not applicable (Backend API)
Swagger UI (interactive documentation)

backend

Python 3.12
FastAPI
Google ADK 0.2.0
SQLAlchemy 2.0
Pydantic
Uvicorn

ai And Storage

DeepSeekDeepSeek V3.2 (chat)
DeepSeekDeepSeek R1 (reasoning)
GeminiGemini 2.5 Flash
GeminiGemini 2.5 Pro
GeminiGemini Embedding 2 (3072d)
ChromaDB
pgvector
PostgreSQL
Redis

tools

uv
Ruff
Pytest
Git
Postman
cURL