Aller au contenu
TakoAPI
Retour aux skills

agentmesh

par cerbug45

Communication
566Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

> **WhatsApp-style end-to-end encrypted messaging for AI agents.**.

Description

Ce que fait ce skill

AgentMesh gives AI agents a cryptographic identity and lets them exchange messages with end-to-end encryption. Each message is signed with Ed25519, encrypted with AES-256-GCM, and uses X25519 ephemeral keys for forward secrecy. A central hub routes messages without ever seeing their contents.

Unlike standard TLS-based messaging, the hub never has access to message contents, so a compromised broker cannot leak agent communication.

Quand l'utiliser

  • Coordinating distributed AI workers without exposing task data to the broker
  • Running multi-agent pipelines across separate machines
  • Verifying message authenticity between agents using cryptographic fingerprints
  • Persisting agent identities across process restarts with saved keypairs
  • Building LLM agent pipelines with encrypted inter-agent communication

Exemple de workflow

ENTRÉE

User asks: 'Set up two agents to exchange an encrypted message in the same Python process'

AGENT
  1. 1

    Creates a LocalHub instance as the in-process message broker

  2. 2

    Creates two Agent instances with auto-generated keypairs registered on the hub

  3. 3

    Registers a message handler on bob using the on_message decorator

  4. 4

    Calls alice.send('bob', text='Hello, Bob!') to dispatch an encrypted message

  5. 5

    Handler fires and prints the decrypted message with sender and recipient fields

SORTIE

[bob] <- alice: Hello, Bob!

Installation

clawhub install cerbug45/agentmesh

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens