Skip to main content

​
Basic Usage

Start a conversation with a chat agent. The response includes a conversation_id you can use to continue the conversation. 
import Reminix from "@reminix/sdk"

const client = new Reminix({ apiKey: "your-api-key" })

const response = await client.agents.chat("support-bot", {
  messages: [
    { role: "user", content: "Hi, I need help with my account" }
  ],
})

console.log(response.output)
console.log(response.conversation_id)

​
Continuing a Conversation

Pass the conversation_id from a previous response to continue the same conversation. Reminix automatically manages the message history. 
// First message
const chat = await client.agents.chat("support-bot", {
  messages: [
    { role: "user", content: "What's my account status?" }
  ],
})

// Follow-up in the same conversation
const followUp = await client.agents.chat("support-bot", {
  messages: [
    { role: "user", content: "Can you update my email?" }
  ],
  conversation_id: chat.conversation_id,
})

​
Parameters

​
agentName
string
required
Name of the agent.
​
messages
Message[]
required
OpenAI-compatible message format. Each message is an object with role and content fields.
​
conversation_id
string
Continue an existing conversation. Omit to start a new one.
​
context
object
Execution context including identity and metadata.

​
Message Format

Messages follow the OpenAI-compatible format with role and content fields. 
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Hello!" },
  { role: "assistant", content: "Hi! How can I help?" },
  { role: "user", content: "What's the weather?" },
]
The system role is optional and typically set by the agent configuration. You can include it to override or augment the agent’s system prompt.

​
Response

​
output
string
The agent’s response text.
​
conversation_id
string
The conversation ID for follow-up messages. Store this to continue the conversation.

​
With Streaming

Pass stream: true to receive the response incrementally as the agent generates it. 
const stream = await client.agents.chat("support-bot", {
  messages: [{ role: "user", content: "Tell me a story" }],
  stream: true,
})

for await (const event of stream) {
  if (event.type === "text_delta") {
    process.stdout.write(event.delta)
  }
}
See Streaming for all event types.

​
Next steps

invoke()

Stateless one-shot calls when you don’t need history.

Conversations

How conversation IDs and identity scoping work.

Error Handling

Catch typed errors and add retries.

Streaming

Event types and SSE format reference.