lookover 0.3.0

Lookover audit logging SDK for AI agents — LangChain and LangGraph integrations

lookover

Audit logging SDK for AI agents. Sends tamper-proof, compliance-ready traces to Lookover — mapped to GDPR, SOC 2 Type II, EU AI Act, and more.

Install

pip install lookover

# With LangGraph support
pip install "lookover[langgraph]"

# With LangChain support
pip install "lookover[all]"

Quick start

from lookover_sdk import LookoverClient, AgentEvent, EventType

client = LookoverClient(
    api_key="lk_...",
    agent_id="my-agent",
    base_url="https://your-lookover-backend.run.app",
)

client.track(AgentEvent(
    event_type=EventType.TOOL_CALL,
    payload={"tool": "calculator", "input": "2+2"},
    outcome="success",
))
client.flush()

LangGraph integration

from lookover_sdk.langgraph import LookoverLangGraphListener

listener = LookoverLangGraphListener(
    api_key="lk_...",
    agent_id="my-graph",
    base_url="https://your-lookover-backend.run.app",
)

result = listener.invoke(graph, {"messages": [HumanMessage(content="Hello")]})

prerun CLI

Scan your agent code for compliance gaps before running it:

prerun scan ./my_agent.py
prerun scan ./agents/ --framework GDPR

Links

• Full documentation
• GitHub
• PyPI