AI Agents work. You make the call.

Druks runs recurring engineering work with the AI tools you already use, then brings each proposed change to you for approval.

No install · Your own Claude or OpenAI account · Approve in Slack

Email me a link for my computeror Install Druks on your AI
Runs / Security sweep · acme/apiWaiting for youRun 4f2a · $0.41
  1. 09:02Read 7 Dependabot alerts in acme/api$0.08
  2. 09:042 alerts touch code you call$0.19
  3. 09:09Upgraded 3 packages in a safe workspace. Tests pass$0.37
  4. 09:10Also checked your GitHub Actions and git history$0.41
⏸ Waiting for your yes

I'd like to upgrade 3 packages in acme/api.

This closes 7 vulnerabilities, 2 of them in code you call. Tests pass. No cost while I wait.

Cost so far $0.41
Works with
  • Claude Code
  • Codex
  • GitHub
  • Slack
  • Linear
  • Jira
Sorin Popa

Why Sherpany runs Druks

Our adoption of agentic operations stalled because we lacked an orchestrator that could run unattended and be trusted: deployed internally, fully auditable. Druks made that real for engineering, and it’s now reshaping how our Customer Success, Sales and Marketing teams operate.

Sorin PopaVP of Engineering, Sherpany
How it works

The work comes to you as one decision.

Druks starts from a schedule, an alert or a button. It stops at the moment that needs a person, and asks you where you already are.

In Slack. Answer from your phone. On Druks Cloud from day one.
Druks APP · 09:10

⏸️ acme/api: 3 package upgrades ready. Closes 7 vulnerabilities (2 in code you call). Tests pass.

ApproveChangeStop
In Claude Code. Approve from the same terminal with Druks MCP.
› anything waiting for me in druks?
Druks is waiting for your approval on acme/api: upgrade 3 packages, closes 7 vulnerabilities.
› approve it
✓ Approved. Druks is opening the pull request.
On the record. Every proposal and decision stays in history with its cost.
✓ Approved by Anna · 09:14

Pull request #142 opened in acme/api. 3 files changed. Cost $0.44.

Security

Your code, your keys, your decision.

What Druks does with your work, and what it does not do.

  • Keys stay out of the agent's workspace

    The agent's workspace never holds your AI or GitHub token. It sees a placeholder. Druks gives the real token only for the call, and it keeps your secrets encrypted.

  • It picks up where it stopped

    After a restart or a deploy, a run continues from its last saved step. Finished work does not run again.

  • Nothing runs while it waits

    When a run asks you, Druks closes its workspace and waits up to 14 days for your answer. No agent runs, so no AI cost.

  • One answer counts

    Each question accepts one answer. A second click or a retry does not approve twice.

  • Every decision on the record

    Each proposal, each answer and its cost stay in the run history.

  • Your server, if you want

    Self-hosted, your code and your data stay on your machine or your server. You can read all of the source code. Report a security problem.

How to Setup

Set it once. Decide when it matters.

Each process is an app with its own schedule or trigger. Example schedule and run data.

ProcessStartsLast runResultNeeds
Security sweepFixes vulnerabilities and hardens your buildEvery Monday 07:00Today, 14 min2 pull requests readyYour yes
Ticket to pull requestWrites, checks and opens the changeTicket labeled "druks"Yesterday, 41 minPull request #188Approved by Anna
Your own processA Druks app is a Python packageYou choose——Read the app guide
Try Druks Cloud

You make the call.

Self-hosted

Run it yourself: paste one prompt into Claude Code. The Druks chat walks you through the rest.

Where Druks runs
On your laptop or your own server

With your AI: paste this into Claude Code or Codex

Or in a terminal

The rest is the same: your own Claude or OpenAI account, and you approve in Slack, the dashboard, the chat or Claude Code.

Questions before you start.

What is Druks?

Druks is a self-hosted or cloud platform where AI agents such as Claude Code and Codex do a company's recurring engineering work, and a person approves each change.

Which AI account does it use?

Your own Claude or OpenAI account. Druks runs the official Claude Code or Codex tools with it. You see the cost after every step.

Can it change my code without asking?

No. A run stops before anything changes in your repositories and waits for your decision, up to 14 days. It costs nothing while it waits.

Is Druks open source?

Druks is source available under the Functional Source License (FSL). You can self-host it, change it and build apps on it. Each release becomes Apache 2.0 two years after it ships.

How is Druks different from n8n, Multica or Copilot?

Druks comes with processes that already run, like the security sweep. The work starts by itself from a schedule or an alert, uses your own AI tools, and reaches you as one decision.

Try Druks Cloud