Agent with Memory and Human‑In‑The‑Loop Confirmation

What this project does

This repository contains a small demo of a LangChain agent that:

1. Remembers the conversation across multiple turns using MemorySaver.
2. Pauses before calling any tool so the user can confirm or cancel the action.
3. Uses the BroJS LLM endpoint (openai/gpt-oss-20b:free).
4. Renders output with the rich library for a pleasant console experience.

File structure

├── main.py          # Entry point – runs three example interactions.
├── agent.py         # Agent definition and helper to run it.
├── requirements.txt # Dependencies (no pinned versions).
└── README.md        # This file.

Installation

pip install -r requirements.txt
export JOURNAL_MCP_PAT=YOUR_BROJS_TOKEN

Running the demo

python main.py

You will see three examples:

1. A simple question that requires no tool.
2. A price query that triggers a confirmation prompt.
3. A follow‑up that demonstrates memory.

Feel free to modify get_price or add more tools – the agent will automatically pause before each call.