Building intelligent systems
that ship securely.

I architect autonomous AI companions and cloud security platforms, from Raspberry Pi edge devices to enterprise-grade deployments.

Active Projects

Building in the open

700+
Phases Built
8700+
E2E Tests
20+
Deployable Apps
AI Agent Teams

Michael Thola

Technology professional building at the intersection of AI, security, and infrastructure.

Michael Thola

DevSecOps Engineer. Builder. Problem solver.

I build systems that work autonomously and reduce my workload by design. Every system I ship follows true DevSecOps procedures: continuously validated, scanned, and hardened. Nothing is vibe coded. Everything is tested.

Currently leading development on EMBER, an autonomous AI companion that runs 24/7 on edge devices, and Crucible Cloud, a platform for deploying and security-auditing any GitHub repository in isolated sandboxes.

I believe the best software is secure by default, observable in production, and built to run without hand-holding.

DevSecOps AI Systems Cloud Architecture Security Engineering Edge Computing Full-Stack

Featured Projects

Systems built from scratch, shipping in production.

EMBER AI Companion AI Companion

EMBER

An autonomous AI companion that runs 24/7 on a Raspberry Pi 5. EMBER sees your screen, remembers context, orchestrates multi-agent teams, and executes complex tasks. A security-first alternative to OpenClaw.

  • 5 specialized AI agent teams with DAG-based orchestration
  • Screen capture + context extraction with encrypted local storage
  • Voice I/O via WhisperX (offline) with expressive animated face
  • Agent Factory: generates new agents on-demand with SonarQube validation
  • Persistent memory with ChromaDB semantic search + temporal decay
  • Self-improvement pipeline with autonomous code generation + rollback
  • Production-grade systemd hardening: watchdog, health checks, auto-restart
Claude API CrewAI Python ChromaDB Raspberry Pi
Crucible Cloud Platform Cloud Platform

Crucible Cloud

A self-service cloud platform for deploying any GitHub repository into isolated, security-audited sandboxes. One-click deployments with built-in compliance scoring, cost analysis, and network monitoring.

  • EMBER compliance engine: SonarQube + Trivy + multi-model AI (OpenAI, Claude, Gemini) with heuristic-based risk scoring (0-100) grounded in real facts
  • Application catalog that grows daily from GitLab trending repos, each auto-evaluated for security
  • Sandbox analysis: clone, scan, AI-assess, approve pipeline for custom repos
  • Private Connect: secure reverse proxy to deployed services
  • Infrastructure visualization with production readiness audits
  • Keycloak SSO with OIDC/SAML, full audit trail, PDF compliance reports
  • 36 passing E2E tests (Playwright) with real service UI validation
React Node.js AWS Docker Keycloak SonarQube

Technologies

Tools and platforms I build with daily.

🧠 AI & ML

Claude API OpenAI Gemini CrewAI Mastra LiteLLM ChromaDB Retrieve-and-Rerank Agent RAG Hybrid RAG Multimodal RAG WhisperX Ollama

Cloud & Infra

AWS Docker Nginx Terraform DynamoDB S3 Lambda

🛡 Security

SonarQube Trivy Keycloak GitLab CE Fernet Encryption MCP OIDC/SAML

💻 Development

Python Node.js React Flask Express PyQt6 Playwright

📋 Agile & Process

Kanban Sprint Planning GitLab CI/CD Story Tracking Code Review

📊 Observability

Prometheus Grafana systemd CloudWatch Structured Logging

Edge & Hardware

Raspberry Pi 5 CM5

Let's Talk

Find me on these platforms or drop a message.