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. 
from reminix import Reminix

client = Reminix(api_key="your-api-key")

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

print(response.output)
print(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
chat = client.agents.chat("support-bot", input={
    "messages": [
        {"role": "user", "content": "What's my account status?"}
    ],
})

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

​
Parameters

​
agent_name
str
required
Name of the agent.
​
input
dict
required
Must contain a messages array. Optionally includes conversation_id to continue an existing conversation.
​
input.messages
list[dict]
required
OpenAI-compatible message format. Each message is an object with role and content fields.
​
input.conversation_id
str
Continue an existing conversation. Omit to start a new one.
​
context
dict
Execution context including identity and metadata.

​
Message Format

Messages follow the OpenAI-compatible format with role and content fields. 
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
str
The agent’s response text.
​
conversation_id
str
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. 
stream = client.agents.chat("support-bot", input={
    "messages": [{"role": "user", "content": "Tell me a story"}],
}, stream=True)

for event in stream:
    if event.type == "text_delta":
        print(event.delta, end="")
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 exceptions and add retries.

Streaming

Event types and SSE format reference.