Capabilities
Active Mirror is a full-stack sovereign AI system. Here's what each layer provides.
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.
Intent classification before inference. Requests categorized and routed based on type and risk.
Continuous SHA256 verification on identity files. Automatic alerts on any mismatch.
Portable identity that works across Claude, Gemini, GPT, Ollama, and any MCP-compatible model. Your AI knows who you are — everywhere.
Temporal · Emotional · Consensus · Retrieval · Vault Sync · Timeline · Mirrors · Recovery · Persona · Collaboration
4,700+ documents indexed with glyph-aware embeddings. Search by meaning, not just keywords.
Every claim tagged as FACT, ESTIMATE, or UNKNOWN. Vault verification required for FACT status.
Use the right model for the right task. Claude for reasoning, Gemini for execution, local models for privacy.
Reflection (Claude) · Execution (Antigravity) · Anchor (Human) — three entities, one coherent operation.
Obsidian vault → ChromaDB → iCloud. Handoffs between sessions. LaunchAgent refresh every 30 minutes.