Capabilities

What Active Mirror Does

Active Mirror is a full-stack sovereign AI system. Here's what each layer provides.

Security Layer

AMGL Guard v1.1

Pre-inference security wrapper. Blocks prompt exfiltration, role injection, and social engineering before the model ever sees the request. Fail-closed — errors block, not allow.

Request Gate

Intent classification before inference. Requests categorized and routed based on type and risk.

Drift Monitor

Continuous SHA256 verification on identity files. Automatic alerts on any mismatch.

Identity Layer

AMI Kernel v1.0

Portable identity that works across Claude, Gemini, GPT, Ollama, and any MCP-compatible model. Your AI knows who you are — everywhere.

10 Core Modules

Temporal · Emotional · Consensus · Retrieval · Vault Sync · Timeline · Mirrors · Recovery · Persona · Collaboration

Memory Layer

Semantic Vault

4,700+ documents indexed with glyph-aware embeddings. Search by meaning, not just keywords.

Truth-State Enforcement

Every claim tagged as FACT, ESTIMATE, or UNKNOWN. Vault verification required for FACT status.

Orchestration Layer

Multi-Model Routing

Use the right model for the right task. Claude for reasoning, Gemini for execution, local models for privacy.

Tri-Twin Architecture

Reflection (Claude) · Execution (Antigravity) · Anchor (Human) — three entities, one coherent operation.

Core Protocols

We didn't just build an app. We invented the standards for sovereign AI.

MirrorDNA™ Protocol

The sovereign identity standard. Defines how AI inherits, verifies, and evolves user identity.

SCD Protocol v3.1

State Continuity Daemon. Ensures memory and context survive across sessions and model switches.

AMGL Guard

Active Mirror Guard Layer. Pre-inference security wrapper that blocks adversarial inputs.

Anti-Hallucination (AHP)

Enforces "Fact vs Estimate" tagging. Prevents the AI from presenting guesses as truth.

Trust-by-Design™

Our architectural philosophy: Fail-closed security, zero-trust data handling, and absolute user ownership.

Reference Rig

The proven hardware stack for full sovereignty. Total cost ~$2,500.

Compute Node

Mac Mini M4 (24GB)

Runs the Vault, local LLMs (Qwen/Llama), and Docker containers. Silent, low power.

Red Teamer

Mac Mini M1 (8GB)

Dedicated adversarial testing node. Runs automated attacks against the security layer.

Mobile Node

Pixel 9 Pro

Runs GrapheneOS. Syncs vault via Syncthing. No Google tracking.

Storage

Samsung T7 Shield

Encrypted backups. Physical data possession. Air-gapped capable.

Proven Capabilities

Verified against the MirrorDNA Capability Registry v1.1 (November 2025).

✓ PROVEN

Code Automation

6 production tools generated. Actual run cost $14 (vs $80 est). 90% efficiency gain.

📂 ✓ PROVEN

Vault Management

557 documents organized. 9+ major versions maintained. Cross-platform sync.

🖥️ ✓ PROVEN

Offline Deploy

Validated on consumer hardware (Mac Mini M4 + Pixel). No datacenter required.

View Full Documentation →