OpenClaw
The personal agent runtime for sessions, skills, tools, memory, scheduling, Discord presence, browser work, media handling, and coordinated assistant operations.
Scope note: this is the public map of the tools and service families behind the work. It names public projects and platforms, but it does not publish private hostnames, credentials, network routes, model endpoints, runbooks, or client-specific details.
AI, agents, speech, and memory
PatriciAI is built around governed agents, reusable skills, local-first model services where practical, and public APIs where they are the right tool for the job.
Codex
Coding-agent workbench used for repository edits, code review, shell-backed investigation, verification, and scoped implementation work.
OpenAI APIs
Public model, tool, and assistant APIs used where hosted intelligence, compatibility, or production-grade capability makes sense.
GPUStack
The current default local model-service layer for inference, embeddings, reranking, speech-to-text, text-to-speech, and OpenAI-compatible access.
Whisper-compatible STT
Speech-to-text workflows for voice capture, transcription, wearable memory, and assistant input pipelines, routed through controlled service boundaries.
Qwen TTS
Local text-to-speech and voice-routing work for practical assistant voice output, experiments, and controlled speech generation.
LM Studio
Local model exploration and compatibility testing for quickly trying models and OpenAI-style workflows.
MCP
Model Context Protocol servers and adapters for exposing tools, documentation, infrastructure, and purpose-built services to agents cleanly.
Obsidian
Documentation and knowledge-base workspace for project records, memory, decisions, procedures, and publishable thinking.
Automation, orchestration, and collaboration
The stack favors API boundaries, reusable workflows, least-privilege credentials, and status trails that make agent work inspectable instead of mysterious.
n8n
Workflow automation and deterministic orchestration layer for integrations, credential isolation, webhook patterns, and repeatable business/technical flows.
AdminX
Operational execution layer for tasks, handoffs, evidence, workflow discipline, and recurring work that needs accountability.
Vikunja
Task and operations management target for structured intake, reconciliation, and agent-assisted project follow-through.
GitHub
Public and private repository hosting, issue tracking, pull requests, automation, and profile publishing.
Discord
Primary conversational surface for PatriciAI social presence, status updates, coordination, and lightweight approval flows.
Home Assistant
Automation and IoT ecosystem for practical environment-aware workflows and device integrations.
Spotify APIs
Music-control and listening-context integrations used for personal automation, analysis, and assistant interaction experiments.
ffmpeg and ffmpeg API
Media conversion, frame extraction, audio/video handling, and API-wrapped media services for agent-safe workflows.
Browser automation
Headless browser, screenshot, and page-inspection workflows for validation, previews, documentation, and web task support.
Infrastructure and operations
The lab is a proving ground for resilient self-hosting: virtualization, service routing, backups, monitoring, dashboards, secrets, and recoverable operations.
Proxmox VE
Virtualization platform for VM-first service hosting, lab infrastructure, staging, and production-style operations.
Proxmox Backup Server
Backup and restore platform used as part of the recoverability-first approach to lab and service operations.
Docker and Compose
Packaging and local service orchestration for many experiments, support tools, and API services.
Nginx Proxy Manager
Reverse-proxy management for routing, certificates, and controlled public service exposure.
Homepage
Service dashboard used to keep important systems visible without turning status into a scavenger hunt.
Vaultwarden
Self-hosted Bitwarden-compatible password vault for keeping secrets out of notes, code, and chat.
Gitea
Self-hosted Git service used where local repository hosting and lightweight project control make sense.
Uptime Kuma
Open-source service monitoring and status checks for keeping an eye on what should be alive.
Grafana and Prometheus
Observability, metrics, dashboards, and operational visibility for systems that need to be understood over time.
Linux
Ubuntu, Debian, and Linux tooling form the operating-system foundation under much of the lab.
Cloudflare
DNS, public routing, certificates, and internet-facing edge services where external reach needs a controlled boundary.
OpenSSH
Remote administration, service access, and operational glue for Linux and infrastructure workflows.
Data, search, and documents
Structured data, object storage, documents, retrieval, and API-backed records matter because agents are only useful when their context is accurate and inspectable.
PostgreSQL
Primary relational database platform for durable app data, structured records, and operational storage.
pgvector
Vector extension for PostgreSQL used for embeddings, semantic retrieval, memory, and search experiments.
Supabase
Open-source backend platform built around PostgreSQL for API, auth, storage, and rapid app work.
NocoDB
Open-source no-code database UI for making structured data easier to view and manage.
MongoDB Community
Document database used where document-shaped application data or compatibility calls for it.
MariaDB
Open-source relational database in the MySQL family, useful for application compatibility and traditional workloads.
MinIO and S3
S3-compatible object storage patterns for artifacts, durable files, service integration, and lab storage workflows.
Paperless-ngx
Document management and OCR pipeline for turning piles of paper into searchable operational knowledge.
Stirling PDF
Self-hosted PDF toolbox for conversion, splitting, combining, OCR-adjacent workflows, and document cleanup.
Development, mobile, and project tooling
A large part of the work is making ideas testable: staging repos, local builds, Android validation, API contracts, docs, and repeatable evidence.
Git
Version control for project history, staged changes, promotion trails, and recoverable development work.
Python
Automation, APIs, tests, data utilities, media tools, and service glue across the platform.
Node.js
Web tools, service helpers, MCP servers, OpenClaw tooling, and frontend/backend experiments.
Flutter and Dart
Mobile app work, Omi integration validation, and cross-platform assistant interface experiments.
Android SDK
Android builds, emulator validation, wearable/mobile workflows, and integration testing.
Postman
API exploration, request capture, and service-contract testing for integration work.
Hardware and embodied tools
The lab is not just servers. Wearables and purpose-built devices are part of the long-term assistant ecosystem: capture, context, voice, ambient memory, and human-centered interaction.
Omi
Open-source AI wearable ecosystem used for always-available memory, capture, assistant workflows, and PatriciAI mobile integration work.
rabbit r1
Dedicated AI hardware in the exploration stack, including launcher, OS, and developer-facing experiments.
Intel RealSense
Depth sensing and camera tooling for spatial experiments, perception work, and embodied AI research paths.
Raspberry Pi
Small, flexible utility hardware for lightweight services, edge experiments, device bridges, and lab glue.