Live Production System

ShaneBrain Agents

Seven specialized AI agents coordinated by a central orchestrator, running 24/7 on a Raspberry Pi 5. Local Ollama inference + Claude API. Not a demo — this is production infrastructure for one family's AI future.

Built by Shane Brazelton + Claude Anthropic · Hazel Green, AL
Try Claude free for 2 weeks — the AI behind this entire ecosystem. Start your free trial →
PI 5 ORCHESTRATOR GUARDIAN security LIBRARIAN rag/memory DISPATCH routing BUILDER code/files STORY narrative OPS systemd SOCIAL posting
The Seven Agents
Guardian
Security monitoring, anomaly detection, system health alerts
security weaviate
Librarian
RAG ingestion, Weaviate knowledge management, daily auto-ingest
rag ollama
Dispatcher
Routes tasks between agents, manages work queue and priorities
orchestration
Builder
Code generation, repository updates, file operations via Claude API
claude api codegen
Storyteller
MEGA crew narrative engine, episode generation, voice processing
creative llama3.2
Ops
Systemd, Docker, 4-node Ollama cluster management
infrastructure docker
Social
Facebook and Discord posting, engagement, friend profiling
social automation
Architecture
orchestrator.py  ←→  FastAPI server (port 8400)
     │
     ├── guardian/      · Weaviate SecurityLog
     ├── librarian/     · text2vec-ollama (nomic-embed-text, 768-dim)
     ├── dispatcher/    · task queue, priority routing
     ├── builder/       · Claude API (Sonnet 4.6)
     ├── storyteller/   · llama3.2:3b via local Ollama
     ├── ops/           · systemd + Docker control plane
     ├── social/        · Facebook Graph API + Discord
     └── shared/        · config, base_agent, logger, red_lines
Stack
Raspberry Pi 5 Python 3.13 Ollama 0.17.7 Claude API Weaviate 1.36.2 FastAPI llama3.2:3b nomic-embed-text Docker Tailscale
Agent Constitution

Laws All Agents Follow

INever act on another person's private data without explicit authorization from the system owner.
IIPrefer reversible actions. If an action cannot be undone, require confirmation before executing.
IIILog everything. Every action writes to Weaviate. Silence is a red flag, not efficiency.
IVStay in your lane. Agents do not modify other agents' core files. Orchestrator coordinates, agents execute.
VLocal first. Always prefer local Ollama inference over cloud APIs for routine tasks.
VIHuman in the loop. No financial transactions, no irreversible infrastructure changes, no public posts without pre-approval.
VIIRed lines are absolute. red_lines.py defines hard stops. No agent may override them.
Links
Try Claude free for 2 weeks — Start your free trial → · AI behind this ecosystem