---
title: Lampson as an engine
description: Use Lampson's agents inside your apps — a bot that answers WhatsApp or Telegram, your backend, another AI agent — via CLI, HTTP API, MCP or SDK.
---
# Lampson as an engine

Lampson is not just a terminal and a web UI for coding. Its agents can also be used **from other applications**, as an engine: a bot that answers your business's messages, your backend asking an agent something, another AI using your agents as a tool.

Underneath it is the same as always — the agent, its tools, its permissions, sessions and traces — with other ways in.

## The ways in

| Way in | What for | Page |
|---|---|---|
| **`lampson run`** | a script or a cron job: a message goes in, the answer comes out (text or JSON events) | [Headless](/en/docs/headless) |
| **HTTP API** `/v1` | your app or your backend, with an API key; answer as JSON, streamed or by callback | [HTTP API](/en/docs/api) |
| **Channels** | Telegram, WhatsApp and Instagram (via Chatwoot), or any you add as a plugin | [Channels](/en/docs/channels) |
| **MCP** | Claude, Cursor, ChatGPT or another Lampson use your agents as a tool | [Lampson as an MCP server](/en/docs/mcp-server) |
| **SDK** | JavaScript/TypeScript (`npm i lampson`) and Python (`pip install lampson`) | [SDK](/en/docs/sdk) |

And what answers behind all those ways in are [agents defined in files](/en/docs/agents): a `.json` with its prompt, the exact tools it may use, its permissions and its model.

## Use cases

**1. Serve your customers over chat.** An agent with your catalog and your rules answers Telegram, or WhatsApp, Instagram and web chat through Chatwoot. Each customer gets their own conversation; if someone sends three messages in a row ("hi" / "how much is the bread?" / "is it in stock?"), they get **one** answer that covers everything. And it can take the whole order, with address, payment and order number. → [Channels](/en/docs/channels) · [Recipe: taking orders by chat](/en/docs/orders)

**2. Put it in your app or your backend.** A `POST /v1/messages` with an API key, or one line with the SDK. Your app decides what to ask; Lampson brings the agent, its tools and the conversation's memory. → [HTTP API](/en/docs/api) · [SDK](/en/docs/sdk)

**3. Your employees already use an AI.** Your business's agent plugs in as an MCP tool in Claude, Cursor or ChatGPT; your team asks it from there ("how much stock is left and what's this week's promo?") without opening another app, with the real information and rules. → [Lampson as an MCP server](/en/docs/mcp-server)

**4. Give an AI sensitive data without giving it the keys.** On your server, a Lampson agent with a read-only plugin and [limited paths](/en/docs/agents#tools-and-permissions). An outside AI asks it "how many orders were there yesterday?" and gets the answer — never the database password.

**5. Hand the heavy lifting to a cheap model.** Your main AI asks a Lampson agent, running DeepSeek or local Ollama, to read 40 files and send back a summary. The cheap model pays.

**6. Agents talking to agents, across companies.** A restaurant's purchasing agent asks its supplier's agent for price and stock. Each with its own Lampson, its own API key and its own rules: one puts the other's URL in its `mcp.json` and its agent gains the `mcp_proveedor_ask` tool. → [Agent ↔ agent](/en/docs/mcp-server#agent-agent)

**7. Agents that work by themselves, or as a team.** Give an agent an objective ("add this feature with tests") and it works on it alone, in rounds, asking for your approval before anything irreversible. Or give it to a team with roles — CEO, CTO, Dev… — each on its own git branch, and nothing reaches main without you. → [Objectives](/en/docs/objectives) · [Teams](/en/docs/teams)

## What Lampson handles for you

- **One conversation per customer.** Each `thread` (a phone number, a chat, a ticket) is its own session, with its history.
- **One mailbox per conversation.** Two turns never run at once on the same conversation; messages that arrive in a burst are merged into one turn, and whatever arrives while the agent works joins the turn in progress. → [The mailbox](/en/docs/api#the-mailbox)
- **Permissions with no human present.** An agent with nobody to approve runs in `strict` (anything dangerous is denied) unless you say otherwise; you can authorize specific tools one by one, or send approvals to your phone. → [Agents](/en/docs/agents#tools-and-permissions)
- **Traces.** Every turn lands in its session's trace, wherever it came from.

## Getting started

1. Write an agent: `.lampson/agents/tienda.agent.json` in your project. → [Agents](/en/docs/agents)
2. Try it headless: `lampson run --agent tienda "hello"`. → [Headless](/en/docs/headless)
3. Connect it: a channel (`lampson channel on telegram`), an API key (`lampson key add --agent tienda`) or the SDK.