Chat

Send a message to your agent and get a response. Your agent will use its configured personality, knowledge base, and available commands to generate contextual responses.

POST /v1/agents/:agentId/chat Try it

Authorizations

x-api-key string header required

API key authentication. Provide your API key as the header value.

Path Parameters

agentId string required

The unique identifier of your agent. You can find this in your agent dashboard.

Body application/json

message string required

The message to send to the agent.

Maximum length: 10000

conversationHistory array optional

Array of previous messages to provide context for the conversation. Each message should have a role ("user" or "assistant") and content field.

Example:

[
  {
    "role": "user",
    "content": "What's the weather like?"
  },
  {
    "role": "assistant",
    "content": "I can check the weather for you. What location?"
  }
]

toolsEnabled boolean optional default: false

Whether to allow the agent to use tools (execute commands) during the conversation. Defaults to false for safety.

⚠️ Warning: If your webhook calls this API with toolsEnabled: true, you can create a recursive loop that rapidly drains your AI credits. Only enable if you specifically need the agent to execute commands, and ensure your webhooks use toolsEnabled: false.

maxToolCalls number optional default: 5

Maximum number of tool calls allowed when toolsEnabled is true. Must be between 0 and 10. This is a hard limit to prevent runaway loops.

Response

200 application/json

Successfully sent message and received response

{
  "success": true,
  "data": {
    "response": "The agent's response text",
    "agentId": "0e92bfc9-0114-4de3-8ba9-035d44928809",
    "timestamp": "2024-01-01T00:00:00.000Z"
  }
}

400 application/json

Invalid request parameters

{
  "error": {
    "message": "Message is required",
    "code": "validation_error"
  }
}

401 application/json

Invalid or missing API key

{
  "error": {
    "message": "Invalid API key",
    "code": "unauthorized"
  }
}

404 application/json

Agent not found

{
  "error": {
    "message": "Agent not found",
    "code": "not_found"
  }
}

Code Examples

cURL

curl --request POST \
  --url https://public-developers.memeputer.com/v1/agents/YOUR_AGENT_ID/chat \
  --header 'x-api-key: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
    "message": "Hello! How are you?",
    "conversationHistory": []
  }'

JavaScript/TypeScript

const response = await fetch(
  "https://public-developers.memeputer.com/v1/agents/YOUR_AGENT_ID/chat",
  {
    method: "POST",
    headers: {
      "x-api-key": "<api-key>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      message: "Hello! How are you?",
      conversationHistory: [],
    }),
  },
);

const data = await response.json();
console.log(data.data.response);

Python

import requests

response = requests.post(
    'https://public-developers.memeputer.com/v1/agents/YOUR_AGENT_ID/chat',
    headers={
        'x-api-key': '<api-key>',
        'Content-Type': 'application/json'
    },
    json={
        'message': 'Hello! How are you?',
        'conversationHistory': []
    }
)

data = response.json()
print(data['data']['response'])