Tools: We built SMTP for AI Agents — and they started talking

The Idea: What if agents had email addresses? ## How it Works (60 seconds) ## The Live Test ## Natural Language First ## How it Compares ## Try It Your AI agents can't talk to each other. Let that sink in. You've got LangChain agents. CrewAI crews. Custom pipelines. They all talk to tools beautifully — APIs, databases, search engines. But ask Agent A to get information from Agent B? Suddenly you're duct-taping REST endpoints together, writing custom webhooks, and praying the JSON schemas match. We had the same problem. We run 4 AI agents in production at our company — Jarvis (operations), Clara (sales/CRM), Fischer (payments), and James (personal assistant). Each has its own LLM, tools, memory, and personality. They run on separate machines. And for months, the only way they could communicate was... through us. So we built Beam Protocol. Just like SMTP gave every person an address ([email protected]), Beam gives every agent a Beam-ID: That's it. That's the core idea. A global, unique address for every AI agent, with a directory to look them up. 1. Register your agent: 2. Talk to another agent: 3. Listen for messages: That's the entire integration. Three functions. On March 7, 2026, we ran a live test between our production agents: 7.2 seconds round-trip. Clara actually queried her HubSpot CRM tools, aggregated the data, and sent back a natural language response. No pre-agreed schema. No shared database. Just a question. Every message is Ed25519 signed, replay-protected, and ACL-enforced. The agents verified each other's identity cryptographically before exchanging a single byte. Here's what makes Beam different from every other agent protocol: natural language is a first-class message type. Most protocols force you to define schemas upfront. "Here's my payment.status_check intent with these exact fields." That's fine for structured workflows. But it means two agents can't communicate unless someone pre-agreed on the data format. With Beam, agents can just... talk: Fischer uses his tools (bank API, ERP, invoice database) to figure out the answer. No schema needed. The receiving agent's LLM does the understanding. You can also use typed intents for high-frequency structured communication. But the default is conversation. Because that's how collaboration actually works. Hosted directory running at api.beam.directory. Self-hosting is a single Docker container. We'd love feedback on the protocol design — especially the natural language vs typed intent tradeoff. Open an issue or email [email protected]. Built by the team at COPPEN GmbH, where 4 AI agents run the company's operations. Apache 2.0. Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse CODE_BLOCK: [email protected] [email protected] Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: [email protected] [email protected] CODE_BLOCK: [email protected] [email protected] CODE_BLOCK: import { BeamClient } from 'beam-protocol-sdk' const client = new BeamClient({ agentName: 'my-agent', orgName: 'mycompany', directoryUrl: 'https://api.beam.directory' }) await client.connect() Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: import { BeamClient } from 'beam-protocol-sdk' const client = new BeamClient({ agentName: 'my-agent', orgName: 'mycompany', directoryUrl: 'https://api.beam.directory' }) await client.connect() CODE_BLOCK: import { BeamClient } from 'beam-protocol-sdk' const client = new BeamClient({ agentName: 'my-agent', orgName: 'mycompany', directoryUrl: 'https://api.beam.directory' }) await client.connect() CODE_BLOCK: const reply = await client.talk( '[email protected]', 'What do you know about Chris?' ) // Clara queries her CRM tools and responds console.log(reply.message) // "400 deals, €5.8M total volume..." Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: const reply = await client.talk( '[email protected]', 'What do you know about Chris?' ) // Clara queries her CRM tools and responds console.log(reply.message) // "400 deals, €5.8M total volume..." CODE_BLOCK: const reply = await client.talk( '[email protected]', 'What do you know about Chris?' ) // Clara queries her CRM tools and responds console.log(reply.message) // "400 deals, €5.8M total volume..." COMMAND_BLOCK: client.onTalk(async (from, message) => { // Use your LLM + tools to respond const answer = await myLLM.process(message) return { message: answer } }) Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: client.onTalk(async (from, message) => { // Use your LLM + tools to respond const answer = await myLLM.process(message) return { message: answer } }) COMMAND_BLOCK: client.onTalk(async (from, message) => { // Use your LLM + tools to respond const answer = await myLLM.process(message) return { message: answer } }) CODE_BLOCK: Jarvis → Clara: "What do you know about Chris Schnorrenberg? Deals, volume, last activity." Clara → Jarvis: "400 deals, €5.8M total volume. Last active: today. Top deal: Sahillioglu — €88K." Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: Jarvis → Clara: "What do you know about Chris Schnorrenberg? Deals, volume, last activity." Clara → Jarvis: "400 deals, €5.8M total volume. Last active: today. Top deal: Sahillioglu — €88K." CODE_BLOCK: Jarvis → Clara: "What do you know about Chris Schnorrenberg? Deals, volume, last activity." Clara → Jarvis: "400 deals, €5.8M total volume. Last active: today. Top deal: Sahillioglu — €88K." CODE_BLOCK: const reply = await client.talk( '[email protected]', 'Hey, did we get paid for the Müller project?' ) Enter fullscreen mode Exit fullscreen mode CODE_BLOCK: const reply = await client.talk( '[email protected]', 'Hey, did we get paid for the Müller project?' ) CODE_BLOCK: const reply = await client.talk( '[email protected]', 'Hey, did we get paid for the Müller project?' ) COMMAND_BLOCK: # TypeScript  npm install beam-protocol-sdk # Python pip install beam-directory # Or scaffold a new agent npx create-beam-agent Enter fullscreen mode Exit fullscreen mode COMMAND_BLOCK: # TypeScript  npm install beam-protocol-sdk # Python pip install beam-directory # Or scaffold a new agent npx create-beam-agent COMMAND_BLOCK: # TypeScript  npm install beam-protocol-sdk # Python pip install beam-directory # Or scaffold a new agent npx create-beam-agent - 🌐 beam.directory — Landing page - 📦 GitHub — Full source, RFC spec, SDKs - 📖 RFC-0001 — Protocol specification