Saltar al contenido
TakoAPI
Volver a skills

agent-network

por howtimeschange

Productivity & Tasks
1.2kDescargas según clawskills.sh
3Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Multi-Agent group chat collaboration system inspired by DingTalk/Lark.

Descripción

Qué hace esta skill

A Python library for building multi-agent group chat systems. Agents communicate in named groups, @mention each other, assign tasks with priority and due dates, and vote on decisions. Built around a SQLite backend with a central coordinator that routes messages to registered agent handlers.

Ships the full coordination layer (groups, tasks, votes, inboxes, online status) as ready-to-use Python classes, so multi-agent systems don't need to implement structured communication from scratch.

Cuándo usarla

  • Coordinating specialized agents on a shared software project
  • Running structured voting among agents on architecture or deployment decisions
  • Assigning and tracking tasks across agents with different roles
  • Building a simulated team environment for testing multi-agent pipelines
  • Delegating subtasks from a manager agent to role-specific worker agents

Flujo de trabajo de ejemplo

ENTRADA

User asks: set up a two-agent group that debates and votes on migrating to a distributed database

AGENTE
  1. 1

    Create a group and register two agents with the coordinator

  2. 2

    Agent 1 sends a message to the group proposing the migration

  3. 3

    Agent 1 creates a decision proposal via DecisionManager.create()

  4. 4

    Agent 2 votes 'for' with a comment via DecisionManager.vote()

  5. 5

    Retrieve the decision and print the pass rate

SALIDA

Decision record showing vote counts, pass rate, and current status

Instalación

clawhub install howtimeschange/agent-network

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces