agent

Agent

An example agent and tool developed using LangGraph and the OCI Python SDK.

Getting started

Start Ollama and pull model

brew services start ollama
ollama pull gpt-oss

Install MCP servers

Authenticate

oci session authenticate --profile-name <profile name> --region <region name: us-sanjose-1>

Setup project

cd agent/app
uv venv -p 3.13
source .venv/bin/activate
uv pip install -e .

Start LangGraph API server

uv run langgraph dev --no-browser --allow-blocking

Interact with the server using the client or API endpoint

Client:

cd ..
uv run client.py

cURL payload.json:

{
  "assistant_id": "agent",
  "input": {
    "messages": [
      {
        "role": "human",
        "content": "What is LangGraph?"
      }
    ]
  },
  "context": {
    "model": "ollama:gpt-oss",
    "base_url": "http://localhost:11434"
  },
  "stream_mode": "messages-tuple"
}

curl -s --request POST \
    --url "http://localhost:2024/runs/stream" \
    --header 'Content-Type: application/json' \
    --data @payload.json

License

Copyright (c) 2025 Oracle and/or its affiliates.

Released under the Universal Permissive License v1.0 as shown at
https://oss.oracle.com/licenses/upl/.

Third-Party APIs

Developers choosing to distribute a binary implementation of this project are responsible for obtaining and providing all required licenses and copyright notices for the third-party code used in order to ensure compliance with their respective open source licenses.

Disclaimer

Users are responsible for their local environment and credential safety. Different language model selections may yield different results and performance.

All actions are performed with the permissions of the configured OCI CLI profile. We advise least-privilege IAM setup, secure credential management, safe network practices, secure logging, and warn against exposing secrets.