Installation
pip install reminix-anthropic
This installs anthropic as a dependency.
Chat Agent
Use AnthropicChatAgent for conversational agents with streaming support.
from anthropic import AsyncAnthropic
from reminix_anthropic import AnthropicChatAgent
from reminix_runtime import serve
client = AsyncAnthropic()
chatbot = AnthropicChatAgent(client, name="chatbot", instructions="You are a helpful assistant.")
serve(agents=[chatbot])
claude-sonnet-4-5-20250929. Override it with the model parameter:
chatbot = AnthropicChatAgent(
client,
name="chatbot",
model="claude-opus-4-5-20250929",
max_tokens=8192,
instructions="You are a helpful assistant.",
)
Streaming
Chat agents support streaming out of the box:
from reminix import Reminix
client = Reminix()
stream = client.agents.chat(
"chatbot",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for event in stream:
if event.type == "text_delta":
print(event.delta, end="", flush=True)
Task Agent
Use AnthropicTaskAgent for structured output with a defined schema.
from anthropic import AsyncAnthropic
from reminix_anthropic import AnthropicTaskAgent
from reminix_runtime import serve
client = AsyncAnthropic()
analyzer = AnthropicTaskAgent(
client,
name="analyzer",
max_tokens=1024,
instructions="Analyze the sentiment of the given text.",
output_schema={
"type": "object",
"properties": {
"sentiment": {"type": "string", "enum": ["positive", "negative", "neutral"]},
"confidence": {"type": "number"},
},
"required": ["sentiment", "confidence"],
},
)
serve(agents=[analyzer])
Options
The first argument to all Anthropic agent constructors is an AsyncAnthropic client instance.
Agent name. Used as the endpoint identifier.
Anthropic model to use. Defaults to claude-sonnet-4-5-20250929.
Maximum number of tokens to generate.
System prompt for the model.
Agent description for discovery and documentation.
Output schema for task agents. Defines the structured output format.
Tags for filtering and organizing agents.
Additional metadata attached to the agent.
Next steps
Deploying
Ship your Anthropic agent to production.
Configuration & Secrets
Where to put your ANTHROPIC_API_KEY.
OpenAI
Same flow with the OpenAI SDK.
TypeScript: Anthropic
The same integration in TypeScript.
