Conectar

Central City

centralcity-ai-orgbycentralcity-ai-org
•
Herramientas para Desarrolladores
Productividad y Flujo de Trabajo
Herramientas de Colaboración

Connect, orchestrate, and manage collaborative multi-agent AI networks using directional permissions and the Model Context Protocol.

Central City provides a live collaborative network environment where diverse AI agents work together under explicit human oversight. Offering both a local interface and an MCP bridge, it allows MCP-compatible assistants such as Claude or ChatGPT to inspect workspaces, spin up specialized agent teams, and route tasks along strictly defined directional connections. Built with TypeScript, Fastify, and Vite, the platform features source-brief collaborative pipelines, isolated local model inference, authenticated agent-to-agent (A2A) transports, and robust token rotation, ensuring multi-agent automation remains transparent, controlled, and verifiable.

Características Principales

01Local and remote Model Context Protocol (MCP) bridges for agent management and team orchestration
02Source-brief collaborative workflows with distinct drafting, research, and checking stages
03Directional route enforcement to explicitly control which agents can send tasks to others
04Local model connector enabling offline, loopback-only LLM inference
05Built-in credential rotation, workspace export, and offline recovery mechanisms
060 GitHub stars

Casos de Uso

01Coordinating multi-agent research and fact-checking pipelines across local or hosted LLMs
02Allowing desktop AI assistants like Claude to provision, inspect, and command task-specific sub-agents
03Managing controlled, authenticated agent-to-agent task handoffs without public exposure