substr8-langgraph

LangGraph adapter for Substr8 RunProof generation.

Installation

pip install substr8-langgraph

Quick Start

from langgraph.graph import StateGraph
from substr8_langgraph import instrument_graph

# Build your graph
graph = StateGraph(...)
compiled = graph.compile()

# Instrument it
instrumented = instrument_graph(
    compiled,
    agent_id="my-agent",
    project="my-project",
)

# Execute - RunProof is generated automatically
result = instrumented.invoke({"input": "hello"})

print(result["run_id"])       # Unique run identifier
print(result["proof_status"]) # "verified" if valid
print(result["proof"])        # Full RunProof object

Features

• Automatic event capture: Tool calls, LLM interactions, node transitions
• Hash chain integrity: Every event is cryptographically linked
• Merkle root commitment: Efficient verification of complete trace
• Sync & async support: Works with invoke() and ainvoke()
• Streaming support: Proof emitted as final event

RunProof Schema

Proofs follow the runproof/v2 schema. See docs.substr8labs.com/sdk for details.

License

MIT