This tutorial runs a LangGraph plan→act agent under Noesis and captures the cognitive artifacts. Governance is off in this demo; the focus is traceability and verification. Why this matters: after one run you have a sealed evidence bundle you can diff and audit.Documentation Index
Fetch the complete documentation index at: https://docs.noesis.systems/llms.txt
Use this file to discover all available pages before exploring further.
What you’ll build
- A LangGraph-backed cognitive run (observe → plan → act → reflect → learn)
- Workspace verification (
verify) and immutable artifacts - A clean episode you can inspect with
noesis view
Prerequisites
- Python with
noesisinstalled - LangGraph installed (
uv add langgraphorpip install langgraph) - OpenAI API key (for the planner/actor)
Run the tutorial
Source
The source file is located atexamples/noesis-quickstart/tutorials/langgraph_episode.py.
