Skip to main content
AgenticPal requires several environment variables for LLM integration, Redis configuration, and session management.

​
Environment Variables

Create a .env file in your project root to store configuration: 
touch .env
Never commit .env files to version control. Add .env to your .gitignore.

​
Required Variables

​
LLM API Configuration

AgenticPal uses LangChain for LLM integration. Configure your preferred LLM provider:
.env
OPENAI_API_KEY=sk-your-api-key-here
Get your API key from OpenAI Platform.

​
Redis Configuration (Optional)

For session persistence and checkpoint storage, configure Redis:
.env
# Redis connection URL
REDIS_URL=redis://localhost:6379

# Session TTL (default: 7 days)
SESSION_TTL_SECONDS=604800

# OAuth state TTL (default: 10 minutes)
OAUTH_STATE_TTL_SECONDS=600

# Session secret for cookie signing
SESSION_SECRET=your-random-secret-here
If you don’t configure Redis, AgenticPal will use in-memory storage. This is fine for CLI usage but required for the web API.

​
Session Secret Generation

Generate a secure random secret for session management: 
python -c "import secrets; print(secrets.token_hex(32))"
Add the output to your .env file:
.env
SESSION_SECRET=a1b2c3d4e5f6...your-64-character-hex-string
If SESSION_SECRET is not set, a random secret will be generated on each startup, invalidating all existing sessions. Always set this in production.

​
Complete .env Example

Here’s a complete example with all variables:
.env
# LLM Provider
OPENAI_API_KEY=sk-proj-abc123...

# Redis Configuration
REDIS_URL=redis://localhost:6379
SESSION_TTL_SECONDS=604800
OAUTH_STATE_TTL_SECONDS=600
SESSION_SECRET=a1b2c3d4e5f6789...

# Optional: Custom paths for OAuth files
# CREDENTIALS_PATH=credentials.json
# TOKEN_PATH=token.json

​
Environment Variables Reference

​
From auth.py

VariableDefaultDescription
CREDENTIALS_PATHcredentials.jsonPath to OAuth client credentials
TOKEN_PATHtoken.jsonPath to cached OAuth token

​
From api/session.py

VariableDefaultDescription
REDIS_URLredis://localhost:6379Redis connection URL (session.py:30)
SESSION_TTL_SECONDS604800 (7 days)Session expiration time (session.py:35)
OAUTH_STATE_TTL_SECONDS600 (10 min)OAuth state expiration (session.py:40)
SESSION_SECRETAuto-generatedSecret for cookie signing (session.py:45)

​
Loading Environment Variables

AgenticPal uses Python’s os.getenv() to read environment variables. Make sure to load them in your application: 
import os
from dotenv import load_dotenv

# Load .env file
load_dotenv()

# Access variables
redis_url = os.getenv("REDIS_URL", "redis://localhost:6379")
Install python-dotenv if not already in your dependencies:
uv add python-dotenv

​
Security Best Practices

1

Never commit secrets

Always add sensitive files to .gitignore:
.env
credentials.json
token.json
2

Use strong secrets

Generate cryptographically secure random secrets:
python -c "import secrets; print(secrets.token_hex(32))"
3

Rotate credentials regularly

  • Regenerate SESSION_SECRET periodically
  • Rotate API keys if compromised
  • Revoke unused OAuth tokens
4

Use environment-specific configs

Maintain separate .env files for development, staging, and production:
  • .env.development
  • .env.staging
  • .env.production

​
Verification

Verify your environment configuration: 
import os
from dotenv import load_dotenv

load_dotenv()

required_vars = [
    "OPENAI_API_KEY",  # or your LLM provider key
]

optional_vars = [
    "REDIS_URL",
    "SESSION_SECRET",
]

print("Required variables:")
for var in required_vars:
    value = os.getenv(var)
    status = "✓" if value else "✗"
    print(f"  {status} {var}")

print("\nOptional variables:")
for var in optional_vars:
    value = os.getenv(var)
    status = "✓" if value else "✗"
    print(f"  {status} {var}")

​
Next Steps

Redis Setup

Set up Redis for session persistence

Build docs developers (and LLMs) love

Get started for freeTalk to us