Sovereign agent infrastructure · trust substrate · formal verification · immersive systems

I build tools that let autonomous agents remember, verify, execute, and leave evidence.

• Persistent memory for agents: High-density Vector Symbolic Architecture (VSA) memory models.
• Verifiable AI systems: Zero-trust containment layers (Epistemic Membrane) using Z3 SMT solvers.
• Distributed cognition: Sovereignty middleware (HMAC-SHA256 obfuscation) for multi-agent swarms.
• Runtime auditability: Append-Only Ledger (AOF) with SHA-256 Merkle chain verification.

Tamper-evident memory, audit trails, and verifiable lineage for AI agents. Operating as an L0 Hypervisor for autonomous agents.

graph TD
    classDef default fill:#0A0A0A,stroke:#2B3BE5,stroke-width:1px,color:#F0F0F0;
    classDef highlight fill:#2B3BE5,stroke:#CCFF00,stroke-width:1.5px,color:#FFFFFF;
    classDef guard fill:#1A1A1A,stroke:#FF0055,stroke-width:1px,color:#F0F0F0;

    subgraph Stochastic Space
        LLM[Agent Stochastic Output]:::default
    end

    subgraph Epistemic Membrane [CORTEX-Persist Containment Shield]
        direction TB
        G1[Z3 SMT Guard / Admission Gate]:::guard
        VSA[Zero-Copy VSA Ring Buffer]:::default
        mmap[( mmap Silicon Space )]:::default
        Hash[SHA-256 Block Sealing]:::default
        Merkle[Merkle Provenance Chain]:::default
    end

    subgraph Trust Substrate
        Ledger[(Append-Only AOF Ledger)]:::highlight
        Proof[Verifiable Audit Pack JSON]:::default
    end

    LLM -->|Decision / Observation| G1
    G1 -->|Passed Asserts| VSA
    VSA -->|Zero I/O Overhead| mmap
    VSA -->|Batch Commit| Hash
    Hash -->|Hash Link| Merkle
    Merkle -->|State Anchoring| Ledger
    Ledger -->|Generate| Proof
    
    style Epistemic Membrane fill:#050505,stroke:#2B3BE5,stroke-dasharray: 5 5;
    style Trust Substrate fill:#050505,stroke:#CCFF00,stroke-dasharray: 5 5;

# Clone and enter the repository
git clone https://github.com/borjamoskv/Cortex-Persist.git
cd Cortex-Persist

# Install in editable mode with development dependencies
pip install -e ".[dev,acceleration]"

# Run the canonical verification and tampering-detection demo
python examples/demo_canonical.py

Sovereign Agentic Architecture Registry — the definitive hub for multi-agent design patterns, including:

• Swarm topologies and inter-agent communication matrices.
• Industrial Noir design tokens for state monitoring UIs.
• Provenance architectures for cryptographic swarm alignment.

A programming language where trust is a compilation invariant. Formally verified smart contracts via Z3 SMT solver.

• Compile-time contract specification check.
• Automatic verification condition generation and logic proofs.

Agent Specification Language (ASL) — open standard for formally specifying and verifying autonomous agent behaviors.

Semantic GUI automation bridge for macOS, enabling natural language intent execution via macOS API hooks.

Sovereign daemon for macOS memory monitoring and RSS budgeting to contain execution spikes.

Homebrew formulas for local daemon installation: brew tap borjamoskv/tap.

Focus:
  - Verifiable Agent Memory & Provenance Layers
  - Formal Verification for Distributed Agent Runtimes
  - Adversarial Testing of Agent Guardrails & Containment Filters
  - Local-first System-level macOS Daemons
Stack:
  Languages: [Rust, Python, TypeScript, Swift, GLSL]
  Verification: [Z3, SMT Solvers, Merkle Tree Chains, SHA-256]
  Substrates: [SQLite Vector, mmap buffers, AOF logs]
  Design: [Industrial Noir 2026, High-Contrast UI, CSS Grid]

• Domain: cortexpersist.com | agents.archi
• Portrait: portrait.so/borja
• Audio Foundry: borjamoskv.bandcamp.com
• Communication: X @bakaladetroya | Instagram @borjamoskv

CORTEX Live Agent Surface

Wake -> Guard -> Store -> Hash -> Verify -> Project