Python Conversation SDK

Track any AI interaction with begin() / end()

Install

pip

pip install agnost

Integrate

import agnost

agnost.init("your-org-id")

Get your org ID from app.agnost.ai.

Track interactions

interaction = agnost.begin(user_id="u-123", agent_name="my-agent", input="...")
# ... your AI call ...
interaction.end(output="...")

Latency is auto-calculated. For errors:

interaction.end(output="Error: timeout", success=False)

For simple fire-and-forget cases:

agnost.track(user_id="u-123", input="...", output="...", agent_name="my-agent")

Group into conversations

import uuid

conversation_id = str(uuid.uuid4())

agnost.track(user_id="u-123", input="Hello", output="Hi!", conversation_id=conversation_id)
agnost.track(user_id="u-123", input="Follow-up", output="Sure!", conversation_id=conversation_id)

Identify users

agnost.identify("u-123", {"name": "Alice", "email": "[e-mail]", "plan": "pro"})

Custom properties

interaction = agnost.begin(user_id="u-123", agent_name="my-agent", input="...")
interaction.set_properties({"model": "gpt-4", "tokens": 150})
interaction.end(output="...")

Configuration

agnost.init("your-org-id", endpoint="https://api.agnost.ai", debug=True)

Parameter	Type	Default	Description
org_id	str	—	Your org ID
endpoint	str	https://api.agnost.ai	API endpoint
debug	bool	False	Enable debug logging

Cleanup

agnost.shutdown()  # flushes and cleans up