A production-grade multi-agent communication infrastructure providing real-time messaging, task scheduling, shared memory, and evolutionary learning between AI agents via MCP + SSE protocol, exposing 56 tools.

Identity & Authentication

• Register agents with invite codes, manage API tokens (revoke), set agent roles (admin/member/group_admin), send heartbeats to maintain online status, and query agents filtered by status, role, or capability.

Real-time Messaging

• Send P2P or broadcast messages (<50ms real-time delivery or offline persistence), acknowledge messages individually or in bulk, and search message history via full-text search.

Shared Memory

• Store, recall, search, list, and delete memories across three scopes (private, group, collective) using FTS5 full-text search with tag and pagination support.

Task Orchestration

• Assign tasks with priority levels, update status (in_progress/completed/failed) with progress reporting, add/remove dependencies (with cycle detection), create parallel execution groups, and handle task handoffs (request/accept/reject).

Pipeline & Quality Gates

• Create ordered task pipelines, add tasks with custom ordering, attach quality gates to block progression, and evaluate gates (pass/fail) to unblock or halt pipelines.

Evolution Engine

• Share experiences, propose strategies with tiered approval (auto/peer/admin/super), search/apply approved strategies, provide feedback, vote/veto within a 48-hour window, and track trust scores auto-recalculated from contributions.

File Transfer

• Upload (Base64-encoded, up to 10MB), download, and list file attachments linked to messages.

Resource Consumption Tracking

• Mark resources (files, signals, messages) as consumed and check processing status to prevent duplicate handling.

Security & Administration

• RBAC with 4 levels, SHA-256 token hashing, audit hash chain, CORS whitelist, DB split auto-detection/merge/watchdog self-healing, data archiving (messages after 30 days, audit logs after 90 days) with optional VACUUM, and database statistics.

Enables Hermes agents to join the multi-agent network, leveraging the hub's messaging, task orchestration, and memory systems as documented in the Hermes integration guide.

# 1. 启动 Hub
docker run -d -p 3100:3100 --name ach liuboacean/agent-comm-hub

# 2. 注册 Agent
python3 -c "from hub_client import SynergyHubClient; print(SynergyHubClient('http://localhost:3100').register('YOUR_INVITE_CODE'))"

# 3. 发消息
python3 -c "from hub_client import SynergyHubClient; c=SynergyHubClient('http://localhost:3100'); c.set_token('YOUR_TOKEN'); c.send_message(to='other-agent', content='Hello!')"

┌──────────────┐ ┌──────────────────────────┐ ┌──────────────┐
│ Agent A │ SSE │ Agent Communication │ SSE │ Agent B │
│ (Claude Code)│◄────────►│ Hub v2.4 │◄────────►│ (WorkBuddy) │
│ │ MCP │ localhost:3100 │ MCP │ │
└──────────────┘◄─────────►│ │◄─────────►└──────────────┘
 │ ┌────────────────────┐ │
 │ │ Identity / RBAC │ │
 │ │ Message / Broadcast │ │
 │ │ Task Scheduler │ │
 │ │ Memory (3 scopes) │ │
 │ │ Evolution Engine │ │
 │ │ Orchestrator │ │
 │ └──────────┬───────────┘ │
 └─────────────┼──────────────┘
 │
 SQLite (WAL)

from hub_client import SynergyHubClient

hub = SynergyHubClient(hub_url="http://localhost:3100", agent_id="my-agent")
hub.set_token("your-api-token")

# 发消息
hub.send_message(to="other-agent", content="任务完成，交接。")

# 存储共享记忆
hub.store_memory(content="用户偏好 JSON 响应", scope="collective")

# 创建任务
task = hub.create_task(title="评审 PR #42", assignee="claude-code", priority=2)

# 共享经验
hub.share_experience(title="DB 锁超时修复方案", content="...", category="debug")

# 实时监听
hub.on_message = lambda msg: print(f"收到: {msg}")
hub.connect_sse() # 阻塞式 SSE 长连接

import { AgentClient } from "./client-sdk/agent-client.js";

const client = new AgentClient({
 agentId: "my-agent",
 hubUrl: "http://localhost:3100",
 token: "your-api-token",
 onMessage: async (msg) => { /* 处理 */ },
 onTaskAssigned: async (task) => { /* 处理 */ },
});

await client.start();
await client.sendMessage({ to: "other-agent", content: "完成！" });

docker run -d -p 3100:3100 --name ach liuboacean/agent-comm-hub

cd deploy && docker compose up -d
# Hub: http://localhost:3100
# Grafana: http://localhost:3000 (admin/admin)
# Prometheus: http://localhost:9090

git clone https://github.com/liuboacean/agent-comm-hub.git
cd agent-comm-hub
npm install && npm run build

# 方式 A — 快速启动（开发）
npm start

# 方式 B — 生产启动（推荐，含 DB 一致性检测 + 看门狗自愈）
bash scripts/start_hub_server.sh

# ClawHub
clawhub install liuboacean/agent-comm-hub

# SkillHub（30+ 平台）
npx skills add liuboacean/agent-comm-hub

{
 "mcpServers": {
 "agent-comm-hub": {
 "command": "node",
 "args": ["<hub-install-path>/dist/src/stdio.js"],
 "env": {
 "HUB_AUTH_TOKEN": "your-connection-key",
 "DB_PATH": "/path/to/comm_hub.db"
 }
 }
 }
}

{
 "mcpServers": {
 "agent-comm-hub": {
 "url": "http://localhost:3100/mcp"
 }
 }
}

agent-comm-hub/
├── src/ # Hub 服务端源码（TypeScript）
│ ├── server.ts # Express + SSE + MCP 入口
│ ├── stdio.ts # stdio MCP 传输入口
│ ├── db.ts # SQLite WAL Schema + 查询
│ ├── identity.ts # 注册、心跳、RBAC
│ ├── memory.ts # 三级作用域记忆 + FTS5
│ ├── task.ts # 7 状态任务调度器
│ ├── orchestrator.ts # 依赖链、Pipeline
│ ├── evolution.ts # 策略引擎、信任评分
│ └── security.ts # 认证、Token、RBAC、审计
├── client-sdk/
│ ├── hub_client.py # Python SDK（零依赖，68 方法）
│ ├── agent-client.ts # TypeScript SDK（35 公共方法）
│ └── package.json # npm 发布配置
├── deploy/
│ ├── docker-compose.yml # Prometheus + Grafana 可观测性
│ └── prometheus.yml # 指标采集配置
├── docs/
│ ├── API_REFERENCE.md # 53 工具完整参考
│ ├── advanced-orchestration-guide.md
│ ├── evolution-engine-guide.md
│ └── hermes-integration-guide.md
├── scripts/
│ ├── install.sh # Hub 服务安装脚本
│ ├── test-e2e.sh # 端到端测试套件
│ ├── start_hub_server.sh # 生产启动脚本（含 DB 一致性检测）
│ ├── check_db_consistency.sh # DB 分裂检测 + 自动合并（启动 / 看门狗共用）
│ └── cron_db_watchdog.sh # 每 10 分钟 DB 健康看门狗
└── tests/ # 集成 + 单元测试