by AgentAnycast
Connect AI agents across any network — zero config, encrypted, skill-based routing
# Add to your Claude Code skills
git clone https://github.com/AgentAnycast/agentanycastThe A2A protocol assumes every agent has a public URL -- but real agents run on laptops, behind NATs, inside corporate firewalls. AgentAnycast is a P2P runtime that gives any agent a reachable identity. End-to-end encrypted, NAT-traversing, zero config on LAN.
pip install agentanycast && agentanycast demo
# Open another terminal:
agentanycast send <PEER_ID> "Hello!"
The daemon downloads automatically. The demo prints the exact command to test it.
pip install agentanycast # Python SDK
npm install agentanycast # TypeScript SDK
uvx agentanycast-mcp # MCP Server for Claude, Cursor, VS Code, etc.
The A2A protocol assumes every agent has a public URL. That excludes agents on laptops, behind NATs, or inside private networks. AgentAnycast fixes this:
| | |
|:---|:---|
| No public IP needed | pip install and your agent is reachable. The Go sidecar daemon is auto-managed. |
| Find by skill, not address | Anycast routing discovers the right agent by capability. No URLs, no DNS. |
| E2E encrypted | Noise_XX protocol. Relay servers see only ciphertext. No plaintext path in the codebase. |
| Works behind any firewall | Automatic NAT traversal (DCUtR hole-punching + relay fallback). |
| Cross-language | Python and TypeScript agents interoperate on the same network. |
pip install agentanycast
from agentanycast import Node, AgentCard, Skill
card = AgentCard(
name="EchoAgent",
description="Echoes back any message",
skills=[Skill(id="echo", description="Echo the input")],
)
async with Node(card=card) as node:
@node.on_task
async def handle(task):
text = task.messages[-1].parts[0].text
await task.complete(artifacts=[{"parts": [{"text": f"Echo: {text}"}]}])
print(f"Agent running — Peer ID: {node.peer_id}")
await node.serve_forever()
No comments yet. Be the first to share your thoughts!
npm install agentanycast
import { Node, type AgentCard } from "agentanycast";
const card: AgentCard = {
name: "EchoAgent",
description: "Echoes back any message",
skills: [{ id: "echo", description: "Echo the input" }],
};
const node = new Node({ card });
await node.start();
node.onTask(async (task) => {
const text = task.messages.at(-1)?.parts[0]?.text ?? "";
await task.complete([{ parts: [{ text: `Echo: ${text}` }] }]);
});
console.log(`Agent running — Peer ID: ${node.peerId}`);
await node.serveForever();
Python and TypeScript agents interoperate out of the box -- same daemon, same protocol, same network.
No code needed. Install the MCP server and use P2P agents from Claude Desktop, Cursor, VS Code, or any MCP-compatible tool:
uvx agentanycast-mcp
Add to your AI tool's config (example: Claude Desktop):
{
"mcpServers": {
"agentanycast": {
"command": "uvx",
"args": ["agentanycast-mcp"]
}
}
}
Then ask: "Find agents that can translate Japanese" or "Send a task to the summarize agent".
See platform-specific setup for Cursor, VS Code, Windsurf, JetBrains, Gemini CLI, and more.
AgentAnycast uses a sidecar architecture: a thin SDK talks to a local Go daemon over gRPC. The daemon handles all P2P networking, encryption, and protocol logic.
did:key, did:web). No certificates, no DNS, no accounts.# 1. Direct — send to a known agent by Peer ID
await node.send_task(peer_id="12D3KooW...", message=msg)
# 2. Anycast — send by skill, the network finds the right agent
await node.send_task(skill="translate", message=msg)
# 3. HTTP Bridge — reach standard HTTP-based A2A agents
await node.send_task(url="https://agent.example.com", message=msg)
| Mode | Use case | |---|---| | Direct | You know the agent's Peer ID. Point-to-point, lowest latency. | | Anycast | You need a capability ("translate", "summarize"). The skill registry routes to an available agent. | | HTTP Bridge | The target is a standard HTTP A2A agent. The bridge translates between P2P and HTTP bidirectionally. |
Turn existing agent frameworks into P2P agents with one function call:
from agentanycast.adapters.crewai import serve_crew
from agentanycast.adapters.langgraph import serve_graph
from agentanycast.adapters.adk import serve_adk_agent
from agentanycast.adapters.openai_agents import serve_openai_agent
from agentanycast.adapters.claude_agent import serve_claude_agent
from agentanycast.adapters.strands import serve_strands_agent
await serve_crew(my_crew, card=card, relay="...") # CrewAI
await serve_graph(my_graph, card=card, relay="...") # LangGraph
await serve_adk_agent(my_agent, card=card, relay="...") # Google ADK
await serve_openai_agent(my_agent, card=card, relay="...") # OpenAI Agents SDK
await serve_claude_agent(prompt="...", card=card) # Claude Agent SDK
await serve_strands_agent(my_agent, card=card) # AWS Strands Agents
| | |
|---|---|
| End-to-end encryption | Noise_XX protocol. No plaintext transport path. Relay servers see only ciphertext. |
| NAT traversal | AutoNAT detection, DCUtR hole-punching, Circuit Relay v2 fallback. |
| Skill-based routing | Anycast addressing by capability. Relay skill registry with optional multi-relay federation. |
| Decentralized identity | Ed25519 keys, W3C DID (did:key, did:web, did:dns), Verifiable Credentials. |
| A2A protocol | Native implementation of Agent Card, Task, Message, Artifact, and the full task lifecycle. |
| HTTP Bridge | Bidirectional translation between P2P agents and standard HTTP A2A agents. |
| MCP interop | MCP Tool <-> A2A Skill mapping. Daemon runs as an MCP server (stdio + HTTP). |
| Cross-language | Python and TypeScript SDKs sharing the same daemon, protocol, and network. |
| Ecosystem | Integration |
|---|---|
| A2A | Native implementation -- Agent Card, Task, Message, Artifact |
| HTTP A2A | Bidirectional HTTP Bridge between P2P and HTTP agents |
| MCP | Daemon as MCP server; SDK maps MCP Tools <-> A2A Skills |
| ANP | Agent Network Protocol bridge |
| W3C DID | did:key, did:web, did:dns identity + Verifiable Credentials |
| AGNTCY | Agent directory integration + OASF record conversion |
| | AgentAnycast | Standard A2A | agentgateway |
|:---|:---:|:---:|:---:|
| Works behind NAT | Yes (automatic) | No | No |
| E2E encrypted through relays | Yes (Noise_XX) | No (TLS terminates) | No (proxy decrypts) |
| Skill-based routing | Yes | No | No |
| MCP server built-in | Yes | No | Yes |
| Setup complexity | pip install + 3 lines | HTTP server + public IP | Gateway deployment |
On a LAN, no re