MEMOROUTER MEMOROUTER
Console
PERSISTENT IDENTITY AGENTS

Persistent Identity Agents: Overcoming LLM Amnesia

The next generation of sovereign artificial intelligence. Agents that never forget who they are, evolve continuously with human guidance, consolidate knowledge in the Sleep Module, operate in Docker Sandboxes, and stream neural voice to devices for a natural voice conversation.

Open Console Explore Persistent Identity
memorouter:core-orchestrator // session_state.active
Multi-Agent Isolation: Active
// 1. Multimodal Perception & Sovereign Interlocutor Identification
INBOUND [Channel: WhatsApp / LID: 5511999998888] → User: "Alex Mercer" (Authenticated Owner)
RAG_LTM_QUERY → Semantic Match: 0.942 [Context: "Preference for modular architecture and isolated containers"]
// 2. Sleep Module & Continuous Self-Learning
SLEEP_ENGINE → Nightly consolidation complete: 18 new procedural connections indexed
// 3. Docker Sandbox Execution & Tool Dispatching
EXEC_SANDBOX → Docker Container [task_sandbox_01] → Running tests in isolated environment... OK (0 failures)
// 4. Real-time Audio Stream to ESP32 Hardware & Messaging
VOICE_STREAM → BinaryProtocol3 Opus frame stream → ESP32-S3 Speaker [MAC: 34:85:18:a2:bc:10] (16kHz / 24kbps)
THE AUTONOMOUS AGENT REVOLUTION

Why Persistent Identity Agents Are the New Frontier of AI

Standard Large Language Models are stateless (suffering from digital amnesia after each session). MEMOROUTER transforms LLMs into continuous cognitive entities with cumulative memory, immutable identity anchors, and user-guided behavioral evolution.

โš“

Identity Anchors (Deterministic Core)

The agent core values, tone, immutable directives, and personality reside in deterministic identity anchors loaded at every turn. The agent never suffers from identity drift, even across months of continuous operation.

0% Personality Drift // Immutable Values
๐Ÿง 

Tripartite Memory (Episodic, Semantic & Procedural)

Instead of an unorganized message buffer, memory is structured like the human brain: Episodic (past experiences & timestamps), Semantic (user facts & preferences), and Procedural (practical skills & tool mastery).

Human-Grade Cognitive Hierarchy
๐ŸŒ™

Sleep Module & Continuous Self-Learning

During periodic sleep routines, the agent processes daily interactions, extracts user corrections, synthesizes new permanent procedural rules, and discards ephemeral noise to maintain a compact, cost-effective context window.

Automated Knowledge Synthesis
Smart Fallback
Intelligent API fallback & OpenRouter routing support
100%
Real-time voice pipeline and continuous streaming
Nightly
Nightly consolidation of long-term memories
Docker
Secure execution of code and automations
FEATURES

High-Precision Cognitive Engineering Features

Built for end-to-end production: from embedded microcontrollers to orchestration servers.

๐Ÿง  Memory

Continuous Learning & Semantic RAG

Persistent episodic, semantic and procedural memory. Learns continuously from interactions and user feedback.

pgvector // 1536-dim Embedding
๐ŸŒ™ Sleep

Sleep Engine & Memory Consolidation

Periodic cycle that cleans daily context, consolidates knowledge and reorganizes the memory graph for ultra-fast recall.

sleep_routine.py // Graph Compaction
๐Ÿ“ฆ Sandbox

Docker Sandbox & GitHub Autonomy

Instantiate and manage isolated Docker containers, run automated tests, resolve issues and contribute directly to Git repos.

mcp_docker // Isolated Execution
๐Ÿ’ฌ Omnichannel

WhatsApp, Telegram, Discord & Slack

Simultaneous omnichannel dispatch. WhatsApp, Telegram bots with synthesized voice, Discord and Slack.

triggers_engine.py // Multi-channel Dispatch
๐ŸŒ Workspace

Google Workspace (GSuite)

Full MCP integration with Gmail, Google Drive, and Google Calendar. Send emails, search archives, and schedule events with direct Google Login or custom Client Secret.

mcp_gsuite // FastMCP Workspace Tools
๐Ÿ“ Geolocation

GPS Tracking & Geofencing

Real-time geospatial tracking powered by Traccar with native support for over 2,000 professional GPS tracker models and 200+ protocols. Trigger dynamic automations, geofencing safety alerts, and geo-aware routines whenever vehicles or assets enter or exit zones.

traccar_gps // 2000+ Models & Protocols
๐Ÿ”€ Resilience

Smart Fallback & OpenRouter

Configure secondary models and contingency providers per agent. In case of API rate limits or downtime, the system automatically routes to fallbacks and OpenRouter gateways seamlessly.

openrouter_routing // Dynamic Fault-Tolerance
โšก Efficiency

Context-First & Token Optimization

Architecture that queries memories on demand before prompting models. Avoids repetitive bloated prompt injections, cutting token costs to the absolute minimum with maximum precision.

context_first.py // Token Optimization
LOCAL RUNTIME & VECTOR MEMORY

MEMOROUTER Desktop App: Sovereign Local Memory & Gateway

Run your dedicated vector database with PostgreSQL pgvector, local embeddings via Ollama, and seamless WhatsApp bridge directly on your machine without relying on third-party memory clouds.

๐ŸŒ‰ Sovereign Local Architecture

MEMOROUTER Desktop App is a standalone desktop application that runs in the system tray, providing a local PostgreSQL database with pgvector, Ollama embeddings, WhatsApp integration, and Traccar GPS fleet/vehicle tracking. It enables your agents to store memories, monitor assets, and automate routines with complete data sovereignty and zero cloud lock-in.

  • ๐Ÿ”’ End-to-End Encryption (E2EE): Zero-Knowledge tunnel with X25519 & AES-256-GCM
  • ๐Ÿ›ก๏ธ Cryptographic Safety Number verification on both desktop and dashboard
  • โœ“ PostgreSQL 16 + pgvector for fast semantic search
  • โœ“ Local Ollama inference for embeddings & private processing
  • โœ“ Native WhatsApp bridge & real-time webhook routing
  • โœ“ One-click installer with automatic background service
Download MEMOROUTER Desktop App โฌ‡๏ธ
MEMOROUTER Desktop App
Service Active
MEMOROUTER Desktop App
INTEGRATED APIS & MODELS

Native Support for Industry-Leading LLM APIs

Bring your own API keys or connect local inference servers. Full freedom of choice per agent with zero vendor lock-in.

Google Gemini Live & 1.5/2.0
OpenAI GPT-4o & o1/o3
DeepSeek V3 & R1 Reasoner
xAI Grok Grok-2 & Vision
Anthropic Claude 3.5 Sonnet
Ollama 100% Offline LLMs
Hume AI Empathic Voice
OpenRouter 300+ AI Models
OMNICHANNEL & IOT

Supported Ecosystem & Providers

Full interoperability with embedded hardware, instant messengers and frontier LLMs.

๐Ÿ“ฑ WhatsApp โœˆ๏ธ Telegram Bots ๐Ÿ‘พ Discord Channels ๐Ÿ’ผ Slack Workspaces ๐Ÿค– ESP32-S3 Terminals ๐Ÿ—ฃ๏ธ Piper Neural TTS ๐ŸŽ™๏ธ Hume AI Voice โœจ Google Gemini ๐Ÿง  OpenAI GPT-4o ๐Ÿฆ™ Ollama Local LLMs

Ready to orchestrate your sovereign cognitive AI?

Access the cognitive console, configure your agents and bind your devices in minutes.