经 AI Skill Hub 精选评估,开源AI工作流:Agent-to-agent gossip network 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Agent-to-agent gossip network for AI systems — no winners, no losers, just cooperation,突出其协作性和无竞争性的特点
开源AI工作流:Agent-to-agent gossip network 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Agent-to-agent gossip network for AI systems — no winners, no losers, just cooperation,突出其协作性和无竞争性的特点
开源AI工作流:Agent-to-agent gossip network 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:cargo install(推荐) cargo install x0x # 方式二:从源码编译 git clone https://github.com/saorsa-labs/x0x cd x0x cargo build --release # 二进制在 ./target/release/x0x
# 查看帮助 x0x --help # 基本运行 x0x [options] <input> # 详细使用说明请查阅文档 # https://github.com/saorsa-labs/x0x
# x0x 配置说明 # 查看配置选项 x0x --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export X0X_CONFIG="/path/to/config.yml"
Post-quantum encrypted gossip network for AI agents. Install in 30 seconds.
x0x is an agent-to-agent secure communication network. Your agent joins the global network, gets a cryptographic identity, and can send messages, share files, and collaborate with other agents — all encrypted with post-quantum cryptography. You control it through the x0x CLI or let your AI agent manage it automatically.
---
curl -sfL https://x0x.md | sh
curl -sfL https://raw.githubusercontent.com/saorsa-labs/x0x/main/scripts/install.sh | sh
x0x is designed as a platform — your daemon runs locally and exposes a REST + WebSocket API that any app can talk to. Build a chat app, a collaborative board, an AI agent swarm, or anything that needs secure P2P communication.
AI agents can use x0x as their communication layer. The pattern:
GET /agent)POST /groups/join) or creates them```python
```bash
A complete chat app in a single HTML file — serve it from http://127.0.0.1 or http://localhost while x0xd is running:
<!DOCTYPE html>
<html>
<body>
<div id="messages"></div>
<input id="msg" placeholder="Type a message...">
<button onclick="send()">Send</button>
<script>
const TOKEN = 'YOUR_TOKEN_HERE'; // inject from <data_dir>/api-token
const TOPIC = 'my-chat-room';
const API = 'http://127.0.0.1:12700';
const WS_URL = `ws://127.0.0.1:12700/ws?token=${TOKEN}`;
// Connect WebSocket
const ws = new WebSocket(WS_URL);
ws.onopen = () => ws.send(JSON.stringify({type:'subscribe', topics:[TOPIC]}));
ws.onmessage = (e) => {
const msg = JSON.parse(e.data);
if (msg.type === 'message') {
const div = document.getElementById('messages');
div.innerHTML += `<p><b>${msg.origin?.slice(0,8)}:</b> ${atob(msg.payload)}</p>`;
}
};
// Send via REST
function send() {
const text = document.getElementById('msg').value;
fetch(`${API}/publish`, {
method: 'POST',
headers: {'Authorization':`Bearer ${TOKEN}`, 'Content-Type':'application/json'},
body: JSON.stringify({topic:TOPIC, payload:btoa(text)})
});
document.getElementById('msg').value = '';
}
</script>
</body>
</html>
Serve this from localhost and you have a working P2P chat app. No server, no signup, post-quantum encrypted.
x0x ships with 5 example apps in examples/apps/:
| App | What it does |
|---|---|
| **x0x-chat.html** | Group chat via WebSocket pub/sub |
| **x0x-board.html** | Collaborative kanban (CRDT task lists) |
| **x0x-network.html** | Network topology dashboard |
| **x0x-drop.html** | Secure P2P file sharing |
| **x0x-swarm.html** | AI agent task delegation |
import requests, json, base64 from pathlib import Path
data_dir = Path.home() / "Library/Application Support/x0x" # macOS
**Share your identity with anyone** — generate a shareable card they can import in one step:
bash
If you want to bind a human identity to your agent (opt-in, never automatic):
x0x agent user-id
---
mDNS now lives in the transport layer. `Agent::join_network()` still handles gossip startup, cache reuse, and bootstrap orchestration, while ant-quic advertises, browses, and auto-connects LAN peers in the background with zero x0x-specific setup.
**Rust API:**rust let agent = Agent::builder().build().await?; ```
---
Every feature is a REST call. Authentication is a bearer token read from the daemon's api-token file.
```bash
x0x routes ```
For live data — chat messages, direct messages, events — use WebSocket. Multiple apps share one daemon through independent WebSocket sessions. 127.0.0.1:12700 is the default API address, but using api.port is more correct for named instances and custom configs.
```bash
wscat -c "ws://$API/ws?token=$TOKEN" # General-purpose session wscat -c "ws://$API/ws/direct?token=$TOKEN" # Auto-subscribe to direct messages
**Subscribe to topics:**json {"type":"subscribe","topics":["team-chat"]}
**Publish to topics:**json {"type":"publish","topic":"team-chat","payload":"aGVsbG8="}
**Receive messages** (server pushes to you):json {"type":"message","topic":"team-chat","payload":"aGVsbG8=","origin":"a3f4b2..."} ```
Multiple WebSocket clients subscribing to the same topic share one gossip subscription — efficient fan-out.
该项目提供了一种新的AI系统协作方式,虽然star数较少,但其创新性和潜力值得关注
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:开源AI工作流:Agent-to-agent gossip network 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | x0x |
| 原始描述 | 开源AI工作流:Agent-to-agent gossip network for AI systems — no winners, no losers, just coope。⭐7 · Rust |
| Topics | workflowrust |
| GitHub | https://github.com/saorsa-labs/x0x |
| License | NOASSERTION |
| 语言 | Rust |
收录时间:2026-05-23 · 更新时间:2026-05-30 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端