musadiqurrahman/whaagent

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

3 stars 0 forks Качество 61 Тренд 24MIT

Multi-tenant WhatsApp AI agent platform — deploy intelligent agents on WhatsApp with LLM support, MCP tools, and production-ready infrastructure.

Обзор

WhaAgent connects AI agents to WhatsApp. A Go gateway handles the WhatsApp protocol. A Python API runs LangGraph-powered agents. Multiple WhatsApp numbers, multiple AI agents, single deployment. Docker builds both the Go gateway and Python API in a single container. Exposes port 8000. - Python 3.12+ - Go 1.21+ - uv package manager Copy .env.example to .env and set your LLM API key: Start the services, then open the QR code page in your browser: Open http://localhost:8000/api/v1/whatsapp/qr/personal/page, scan with WhatsApp (Settings > Linked Devices). WhaAgent ships with 12 built-in agents. Each agent has a system prompt, tool access, and can be customized. Assign agents to WhatsApp numbers in ~/.whaagent.yaml:

README

Показан фрагмент оригинального README. Открыть оригинал.

Overview

WhaAgent connects AI agents to WhatsApp. A Go gateway handles the WhatsApp protocol. A Python API runs LangGraph-powered agents. Multiple WhatsApp numbers, multiple AI agents, single deployment.

User sends WhatsApp message
        |
        v
Go Gateway (whatsmeow) --> Python API (FastAPI) --> AI Agent (LangGraph)
        |                                                  |
        v                                                  v
Response sent back via WhatsApp                    Tools / LLM / Memory

Architecture

flowchart TB
    subgraph Clients["Client Layer"]
        WA1["WhatsApp User A"]
        WA2["WhatsApp User B"]
        WA3["WhatsApp User C"]
    end

    subgraph Gateway["Go Gateway"]
        SM["Session ManagerMulti-tenant WhatsApp connections"]
        QR["QR Code GeneratorSSE streaming to browser"]
        EVT["Event HandlerAsync message processing"]
        HTTP["HTTP ClientForward to Python API"]
    end

    subgraph API["Python API — FastAPI"]
        ROUTE["Webhook Router/api/v1/channels/whatsapp/message"]
        AUTH["API Key AuthX-API-Key header"]
        POOL["Tenant Agent PoolLRU eviction, per-tenant isolation"]
        DB["SQLite CheckpointConversation memory persistence"]
    end

    subgraph Graph["LangGraph StateGraph"]
        SUM["Summarize NodeToken threshold, context compression"]
        ROUTER["Router NodeLLM intent classification"]
        AGENT["Agent NodeTool orchestration, ReAct loop"]
    end

    subgraph Agents["Agent Registry"]
        A1["assistantGeneral-purpose orchestrator"]
        A2["developerCode exploration and analysis"]
        A3["news / br-news / es-newsNews aggregation"]
        A4["learning / recipe / youtubeDomain-specific agents"]
        A5["github-pr-reviewerPull request automation"]
        A6["Custom [email protected]"]
    end

    subgraph Tools["Tool Layers"]

Открыть полный README на GitHub