SYSPhONY
Distributed Artificial Neural Network for AI Agents
MCP aggregator · Model-agnostic · Cluster fabric
github/GenesysHub ↗
sysphony
/ˈsɪs.fə.ni/
noun
Definition
  1. The coordinated, harmonious integration of multiple systems, components, or processes functioning as a unified whole.
  2. (Figurative) A complex and elegant arrangement of interconnected parts operating seamlessly, akin to a symphony orchestra.
Sysphony platform — modern definition

A living cognitive architecture that elevates AI agents from stateless responders to autonomous, persistent entities with cross‑session memory, universal tool federation, and real‑time event mesh. Model-agnostic (OpenRouter, Ollama, OpenAI, Anthropic, any OpenAI-compatible endpoint) and database-flexible (SQLite, MongoDB, PostgreSQL).


About · The cognitive fabric

Sysphony breaks the chatbot paradigm. It provides a distributed neural network where AI agents possess long‑term memory, tool-based agency, collaborative workflows, and a real‑time execution layer — across any client, any model, any session.

At its core, Sysphony is an Model Context Protocol (MCP) aggregator and horizontal execution mesh. You can plug any MCP server — built‑in or external — to construct custom agent workflows. The platform federates tools (memory, file, browser automation, search, arithmetic, agent invocation, etc.) and lets you compose them visually or via code. Works with any MCP client: Claude Desktop, Cursor, Codex, Kiro, and any custom client.

Under the hood: an Express + WebSocket monolith that scales via role separation (state server for persistence and real‑time events, stateless compute nodes for agent/tool execution). Supports SQLite, MongoDB, or PostgreSQL — choose your persistence layer. From solo mode (single process) to full cluster on AWS, the same Docker image runs everywhere.


Architectural evolution · Operational phases
Foundation & extraction Active
Cluster backbone, MCP server, core workflow engine. State/compute split, HMAC registration, round‑robin routing, WebSocket event relay.
MCP Hub & tool federation In progress
Universal MCP aggregator. Register any external MCP server, compose super‑tools, workflow designer with MCP nodes. Public registry and agent‑driven discovery.
Genesys semantic memory Concept
Cross‑session memory & rule engine. Embedding vectors, hybrid search, episodic recall. Agents remember conversations, decisions, and learn across invocations.
Generative UI · visual cortex Concept
Agents render their own interface. Dynamic, data‑driven components. Agent‑controlled dashboards and real‑time layout mutation.
Synapse network · hive mind Concept
Multi‑agent mesh with async message passing. Fractal orchestration, emergent collaboration, 3D brain visualization, cross‑agent learning.

Scaling model — State server (persistence, WebSocket hub) + stateless compute nodes (auto‑register via HMAC). Compute nodes execute workflows and agent calls, events relay to state → broadcast to frontends. Local solo mode for development, production cluster scales horizontally on AWS ECS Fargate.


Core capabilities · MCP aggregator in action

MCP federation

Built‑in tools: memory, workflows, filesystem, browser automation (Stagehand), fetch, search, agent invocation. Add any external MCP server — universal aggregator. Learn more at MCP official.

Model‑agnostic AI

Use OpenRouter, Ollama, OpenAI, Anthropic, Groq, local models — any OpenAI‑compatible endpoint. No vendor lock‑in.

Multi‑database

Support for SQLite (default), MongoDB, and PostgreSQL. Choose your persistence backend.

Workflow designer

Visual node graph with MCP steps, conditional branches, parallel execution. Stream results, parameter resolution. Built on React Flow.

Persistent agents

Autonomous entities with long‑term memory, skill sets, and message‑based collaboration. Cross‑session recall via native vector embeddings stored directly in your SQLite, MongoDB, or PostgreSQL database.

Generative UI · agent‑injected layouts

Agents can discover available UI components, render new components on the fly, and mutate page layouts in real time. Dynamic, data‑driven interfaces controlled entirely by agent logic.

Real‑time event mesh

WebSocket channels: execution_events, tool_activity, agent messages, app_state. Compute → state relay ensures live UI updates and agent‑frontend sync.

MCP client‑agnostic

Works with Claude Desktop, Cursor, Codex, Kiro, any MCP client. Standard Model Context Protocol.

Cluster ready

Same Docker image, role env (state / compute / solo). HMAC peer registration, heartbeat, execution routing. Deploy on EC2 + ECS Fargate.

Bun Express MCP OpenRouter / Ollama SQLite / MongoDB / PostgreSQL Next.js static export Legend State WebSocket AWS (EC2 + ECS Fargate) HMAC cluster auth Playwright/Stagehand
distributed neural network · bootstrapping synapse fabric