Filesystem Context

This example shows DeepAgents using explicit filesystem-style paths for context instead of hidden state. /memories/AGENTS.md is loaded as startup memory, and /workspace/notes.md lives in a routed workspace backend.

Requirements

• Python 3.10+
• An OpenAI API key set as an environment variable (OPENAI_API_KEY)

Steps for running this example in the shell

1. Install dependencies:

python -m venv .venv

# macOS/Linux:
source .venv/bin/activate

# Windows Command Prompt:
.venv\Scripts\activate.bat

# Windows PowerShell:
.venv\Scripts\Activate.ps1

pip install -r requirements.txt

2. Export your API key as an environment variable:

export OPENAI_API_KEY="sk-..." # Windows cmd: set OPENAI_API_KEY="sk-..." # Windows PowerShell: $env:OPENAI_API_KEY="sk-..."

3. Run the script:

python filesystem_context.py

Output

Seeded /memories/AGENTS.md and /workspace/notes.md.