Neural Memory
A local-first personal cognitive memory assistant and second brain for macOS.
Transforms human desktop context into an autonomous, searchable knowledge graph — anchoring decisions, tracking commitments, and exposing context directly to AI tools via MCP.

⚡ Quick Start: Choose Your Track
Zero prerequisites. No Docker, no Python, no Homebrew, no terminal required.
- Download
NeuralMemoryAgent-0.2.0-Installer.dmg(approx. 112 MB). - Open the disk image and drag
NeuralMemoryAgent.appto your Applications folder. - Launch the app from Applications. The built-in Visual Setup Wizard guides you through the minimal required macOS entitlements.

Read the full Standalone Installer Guide.
Full Docker Compose + Neo4j 5.26 Community Graph Database.
- Diagnostic verification:
./scripts/doctor.sh - API health:
http://127.0.0.1:8765/health - Neo4j Browser:
http://127.0.0.1:8774 - Full test suite:
make test-massive
🌟 Key Capabilities
🔒 PrivacyShield Local Redaction
In-memory regex and Luhn checksum filtering automatically masks credit cards, IBANs, API keys (sk-..., AIza..., GitHub tokens), and passwords before persistence or optional LLM enrichment. Sensitive vaults (1Password, Bitwarden, Keychain) are permanently denied.
🎯 Contextual Micro-Feedback Anchoring
Eliminates arbitrary length cutoffs. Assents like "Ok, procedi con l'offerta da 5000€" are anchored to the sender, document, and decision terms.
🌌 Temporal Knowledge Graph
- Topic Clusters: Force-directed layout with orbital regional gravity clusters related thoughts into thematic galaxies without central collapse.
- Timeline Stream: Horizontal chronological axis with 5 vertical semantic altitude lanes (Reflections, Decisions, Meetings, Commitments, Topics).
- Time Scrubber: Interactive slider to replay memory history with Ebbinghaus memory decay ($R = e^{-\Delta t / S}$).
🤖 Model Context Protocol (MCP)
Native stdio server providing tools for Claude Desktop, Cursor, and Antigravity: recall_decisions, recall_commitments, recall_meetings, get_daily_briefing, and search.
📚 Documentation Navigation
-
Deep technical dive into the Dual-Track execution model, data pipelines, and storage engines.
-
Step-by-step installation, permissions setup, and clean-environment testing on macOS.
-
Orbital physics model, semantic altitude lanes, time scrubber, and Ebbinghaus decay.
-
Entity schemas (
Decision,Commitment,Meeting,Reflection), relationship semantics, and queries. -
Tool schemas and configuration guides for Claude Desktop, Cursor, and Antigravity.
-
Data flow guarantees, deny-lists, masking algorithms, and ephemeral event pruning.
-
The 5-stage massive test battery (
make test-massive) and clean simulation (make verify-clean).