SanctumOS Architecture
SanctumOS is a self-hosted cognitive operating system for agentic AI. Its design is explicitly neuro-inspired, borrowing metaphors from human cognition while applying them to modular, auditable AI infrastructure.
Core Design Principles
- Self-Hosting: All components run on personal hardware or small servers
- Transparency: Every subsystem logs provenance for accountability
- Extensibility: Plugin and modular design for easy extension
- Neuro-Inspired: Subsystems mapped to cognitive functions
- Governance First: MCP governs permissions and orchestration
- Privacy by Default: No third-party centralized infrastructure
Cognitive Architecture
Thalamus
Function: Preprocessing hub for raw inputs
- Phase 0: Immediate pass-through to Cerebellum
- Phase 1: Cleanup, autocorrect, re-segmentation
- Phase 2: Semantic annotation, topic tagging
Cerebellum
Role: Real-time filtering and prioritization
- Low-latency event-driven filtering
- Gut-check reflex arcs
Basal Ganglia
Role: Task selection and control loop management
- Arbitration among competing sub-agent goals
- Enforces success/fail loop structures
Conscious Mind
Core Agent: Central conversational and reasoning engine
- Maintains core memory and recall memory
- Coordinates sub-agents through MCP
Dream Agent
Role: Nightly summarization and long-term integration
- Hippocampus: Summarizes recent activity
- Neocortex: Consolidates into long-term structures
- Glymphatic System: Compacts indexes and prunes data
System Architecture
%20(10)_image_1.png)
Memory Management
- Core/Recall Memory: Active conversational state
- Archival Memory: SQLite-backed persistent store
- Summarization Cycles: Regular pruning and integration
- Infinite Context DB: Token usage tracking and context windows
Communication Layer: Broca 2
Design: CLI-first, plugin-based message processor
- Translates agent decisions into platform-specific messages
- Plugin system for endpoints (Telegram, CLI, APIs)
- Message queue with echo, listen, live modes
- MCP-scriptable commands
Multi-Agent Ecosystem
- Deep Research Agent: Structured analysis and synthesis
- Internal Monologue Agent: Reflective insights generation
- Dream Agent: Summarization and archival maintenance
- Cerebellum: Input prioritization and filtering
- Proactive Outreach Agents: Condition/time-based triggers
Key Benefits
Privacy & Control
- Complete data control through self-hosting
- No external dependencies
- Transparent operations
Scalability & Performance
- Modular design for independent scaling
- Efficient memory management
- Intelligent resource allocation
Extensibility
- Plugin architecture for new capabilities
- MCP integration for standardized tools
- Open source for full customization
Development Philosophy
SanctumOS follows a neuro-inspired design that maps software components to cognitive functions, ensuring intuitive and predictable behavior that mirrors human cognitive processes.
Naming Convention
Our Naming Rubric ensures consistent terminology across the system:
- Neuroanatomical names for cognitive components (Thalamus, Basal Ganglia, Dream Agent)
- Technical names for infrastructure (MCP, UI, Kernel)
- Industry terms for AI/ML extensions (agents, tools, memory blocks)
- Mythic names for agent personalities (Athena, Monday, Sentinel)
Next Steps
- Install: Use the forthcoming Master Sanctum Installer or follow individual repo installation instructions
- Configure: Set up your first agent
- Explore Components: Start with the Components Overview or dive into Thalamus, Basal Ganglia, and Dream Agent
- Explore Modules: Learn about Sanctum Letta MCP and Broca-2
- Extend: Build custom plugins
SanctumOS Architecture - A neuro-inspired approach to self-hosted AI agent systems.