Skip to main content

Romek

Romek

Persistent auth for AI agents. Works on any site, today.

No website integration required. No OAuth adoption needed. Just secure session management that works.

License: MIT PyPI version Python 3.8+ Dev.to

Quick StartLangChainn8nHow It WorksRoadmap


The Problem

# What every agent developer does today
cookies = {"session_id": "abc123..."}  # Hardcoded. Breaks constantly. Security nightmare.

Sessions expire. Cookies leak into git history. No audit trail. No access control.

The Solution

from romek import Vault

vault = Vault()
cookies = vault.get_session("linkedin.com")  # Encrypted. Scoped. Audited.
pip install romek

Works on sites as they exist today. No website changes. No OAuth adoption. No waiting for the ecosystem.


See It In Action

One command to grab cookies from Chrome

Agent automatically authenticates using stored session—no manual login, no hardcoded cookies.


How It Works

  1. Log into any site in Chrome (you probably already are)
  2. Run romek grab <domain> — cookies are encrypted and stored locally
  3. Your agent retrieves them securely on-demand

No extension required. No copy-paste. One command.


Quick Start

pip install romek
romek grab linkedin.com

That's it. Your LinkedIn session is now stored in an encrypted vault.

The grab command reads cookies directly from Chrome—no extension needed, no manual export.

from romek import Vault

vault = Vault()
cookies = vault.get_session("linkedin.com")

# Use with requests, Playwright, or any HTTP library
import requests
response = requests.get("https://linkedin.com/feed", cookies=cookies)

Works with any site you're logged into:

romek grab github.com
romek grab notion.so
romek grab twitter.com

Multiple Chrome Profiles

If you use multiple Chrome profiles, specify which one to grab from:

romek grab linkedin.com --profile "Profile 1"
romek grab github.com --profile "Work"

To find your profile names:

# Mac
ls ~/Library/Application\ Support/Google/Chrome/

# Linux
ls ~/.config/google-chrome/

# Windows
dir %LOCALAPPDATA%\Google\Chrome\User Data\

Default profile is used if no --profile flag is specified.


☁️ Remote Servers (VPS / Headless / Docker)

Running n8n or scripts on a server without Chrome? Sync your local session:

On your local machine:

romek grab linkedin.com
romek export linkedin.com -o cookies.json

Copy to server:

scp cookies.json user@your-server:~/

On your server:

pip install romek
romek import cookies.json --domain linkedin.com

Your server can now access your authenticated sessions.


Project Config (Team Workflows)

Define sessions your project needs in a config file:

romek init

Creates romek.yaml:

sessions:
  - linkedin.com
  - github.com
  - gmail.com

Then sync all sessions at once:

romek sync

Check health of all project sessions:

romek doctor

Output:

Checking session health...

linkedin.com
├── Status: ✅ Fresh
├── Cookies: 26 stored
└── Expires: in ~4 weeks

github.com
├── Status: ✅ Fresh
├── Cookies: 16 stored
└── Expires: in ~4 weeks

Health: 2/2 sessions ready

Share romek.yaml with your team. Each dev runs romek sync locally.


Why Romek?

Without Romek With Romek
Hardcoded cookies in code Encrypted vault storage
Sessions in git history Secrets separate from code
Any code can access anything Scoped access per agent
No idea what accessed what Full audit logging
Sessions break silently Expiration notifications

LangChain Integration

from langchain_openai import ChatOpenAI
from langchain.agents import initialize_agent, AgentType
from romek.langchain import get_romek_tools

tools = get_romek_tools(
    agent_name="sales-bot",
    vault_password="your-vault-password"  # Password auto-retrieved from system keyring if not provided
)

llm = ChatOpenAI(model="gpt-4", temperature=0)
agent = initialize_agent(
    tools=tools,
    llm=llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True
)

# Agent automatically uses stored sessions
response = agent.run("Get my LinkedIn notifications")

Available tools:

  • authenticated_request — Make HTTP requests with stored session cookies
  • get_session_cookies — Retrieve cookies for custom requests

n8n Integration

Use Romek in your n8n workflows with our community node.

npm install n8n-nodes-romek

The node lets you:

  • Store and retrieve session cookies in n8n workflows
  • Use authenticated sessions with HTTP Request nodes
  • Build automation flows that require login

📦 View on npm | GitHub


Playwright Integration

from playwright.sync_api import sync_playwright
from romek import Vault

vault = Vault()
cookies = vault.get_session("github.com")

with sync_playwright() as p:
    browser = p.chromium.launch()
    context = browser.new_context()
    context.add_cookies(cookies)
    
    page = context.new_page()
    page.goto("https://github.com/notifications")
    # Already authenticated!

CLI Reference

Command Description
romek grab <domain> Grab cookies from Chrome
romek grab <domain> --profile "Name" Grab from specific Chrome profile
romek list List all stored sessions
romek delete <domain> Delete a stored session
romek refresh <domain> Re-grab cookies for a domain
romek init Create romek.yaml config file
romek sync Grab all sessions from romek.yaml
romek doctor Check health of all project sessions
romek status <domain> Check status of a specific session
romek export <domain> -o file.json Export cookies to JSON file
romek import <file> --domain <domain> Import cookies from JSON file
romek version Show current version

Security

  • AES-256 encryption with PBKDF2 key derivation (100k iterations)
  • Ed25519 keypairs for agent identity
  • Scoped access — agents only access approved domains
  • Audit logging — every access logged with timestamp
  • SQLite storage — encrypted database at ~/.romek/vault.db

Roadmap

  • Chrome extension for cookie export (replaced by grab command)
  • Encrypted local vault
  • Direct Chrome cookie extraction (romek grab)
  • Playwright integration
  • LangChain integration
  • n8n integrationn8n-nodes-romek
  • Project config (romek.yaml)
  • Session health checks (romek doctor)
  • Export/Import for remote servers
  • Firefox extension
  • Selenium examples
  • Cloud vault sync

Examples

Working demos available in the examples/ folder.

GitHub Agent Demo

Setup:

# 1. Create the agent
romek create-agent github-agent --scopes github.com

# 2. Grab cookies from Chrome
romek grab github.com

# 3. Your session is now stored and ready to use

Run:

PYTHONPATH=. python examples/github_agent.py

Contributing

PRs welcome. Check out the issues for feature requests.


License

MIT

Star us if Romek helps your agents authenticate!

Release files for romek 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for romek 0.4.0
File Size Uploaded
romek-0.4.0.tar.gz 27.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for romek 0.4.0
File Interpreter ABI Platform
romek-0.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 55.2 kB

Release files / romek-0.4.0.tar.gz

Download URL romek-0.4.0.tar.gz
Size 27.2 kB
Tags Source
SHA-256 checksum
How to use checksums
62e6c5f0a2852b0b566a8ddb065861ed77ac5af6b1c282b2f1902a751771f12e
BLAKE2b-256 checksum
How to use checksums
6ce787db8e75953b8cb256dff3583f771f3de931b0c21f4e150606b173e77326
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.6

Release files / romek-0.4.0-py3-none-any.whl

Download URL romek-0.4.0-py3-none-any.whl
Size 28.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a4453072e4860fadd3f396b9d1099e1ef59baedc471ae0edebd678140057601a
BLAKE2b-256 checksum
How to use checksums
dda0025f82b0342d62aa853b60bd72aa42f701a743013a26428cd82e70afc5ab
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.6

Release history Release notifications | RSS feed

This release

0.4.0 This release

2 release files

0.3.2

2 release files

0.3.1

2 release files

0.3.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page