• 100% Open Source
  • 100% Free
  • 100% Local

Babysit AIAutonomous AI

Make the important decisions, let AI do the rest.

Dashboard
Try:$ npx @openagt/dashboard# One-shot (no install)pnpm dlx @openagt/dashboard# One-shot (no install)bunx @openagt/dashboard# One-shot (no install)yarn dlx @openagt/dashboard# One-shot (no install)Or install:$ npx @openagt/installpnpm dlx @openagt/installbunx @openagt/installyarn dlx @openagt/install
The OpenAgent dashboard: an agent's run asks which way to go, its recommended answer picked, beside the project's pages and runs.
What is it?

It turns AI agents into autonomous teammates that handle work end-to-end — while you stay in control of key decisions.

Any software

(Semi-)autonomously build anything from simple web apps to complex software.

On this page

Stop babysitting

Problem

AI is lazy

Bad fix

Appending "DON'T BE LAZY" to your prompts → minimal improvement.

Solution

Divide-and-conquer: OpenAgent instructs AI to split large tasks into smaller subtasks. By focusing on one unit of work at a time, AI spends significantly more effort overall, resulting in much higher-quality output.

Solution

Coverage guarantees: OpenAgent lets AI enumerate everything that needs to be done before writing code. AI then works through that checklist, ensuring comprehensive coverage and preventing lazy shortcuts.

Problem

Lazy AI plans

Bad fix

Explicitly tell AI to deep dive important aspects.

Solution

Automatic loop of critical feedback ↔ research ↔ confidence ↔ implementation.

Problem

Lazy low-quality code

Despite AI being able to write high-quality code, it often goes for the quickest/laziest solution (not correct, not maintainable, not DRY).

Bad fix

Appending "WRITE CLEAN CODE" to your prompts → minimal improvement.

Solution

When an agent makes complex changes, the agent adds post-merge refactoring prompts to the AI Queue (with low priority).

Solution

Automatic routine security and code quality prompts (when your usage quota has plenty of capacity).

Problem

AI makes important decisions without asking

Bad fix

Tell AI "don't do this, research alternatives".

Solution

OpenAgent makes AI self-gauge its confidence before starting to work.

Solution

It also makes AI self-gauge the variability of its plan: if there are alternatives with subtle pros and cons, show them to the user.

Problem

AI forgets

Bad fix

You keep repeating yourself (previous decisions, business context, …).

Solution

AI retains knowledge via files such as knowledge-base/DECISIONS.md and knowledge-base/INSIGHTS.md.

Autonomous AI

Focus on what matters, let AI do the rest.

Autonomous Product Management

Let AI autonomously:

  • Test & review
  • Research, plan, and prioritize your tickets
  • Turn your team conversations into tickets
  • Coming soon Save your team conversations to conversations/<DATE>_<TOPICS_SLUG>.md
  • Market research

Autonomous Coding

Let AI autonomously implement:

  • Quick-wins
  • Quality refactoring
  • UX improvements
  • Consensual work

Note Agents still ask for your confirmation for non-obvious decisions.

Note You're still in control — only pick the autonomicity that works for you.

The dashboard's Tickets page: the project's two tickets, Dark mode and Login page, and its presses to add them to the queue.

How it works

OpenAgent introduces one major building block:

Queues

AI Queue

Queue of upcoming AI tasks — tasks are added by humans, or by agents (autonomously if no uncertainty, or after human confirmation otherwise).

Agents autonomously populating the AI queue is what makes AI autonomous.

Technically, it's just a TODO_AGENTS.md file in your Git repositories.

Human Queue

Queue of pending human reviews — populated when agents need you to review (important) decisions with subtle pros and cons.

It's your cockpit — it keeps humans in control.

The dashboard's Waiting on you: a run that needs an answer to Which way?, and one with a commit that needs a push.

Note Everything is powered by open source state-of-the-art prompts (you can also bring your own):

Security auditCode qualityResearchProduct ManagementAdd yours

Features

  • Bring your own subscription

    Use your AI subscription — OpenAgent orchestrates agents via your Claude Code / Codex installation, like humans do.

  • Optimal quota usage

    Stop wasting unused quota — OpenAgent drives AI autonomy for optimal quota usage: maximum daily usage while keeping enough quota space for manual prompts.

  • Bring your own prompts

    Save and quickly re-use your favorite prompts. Share them with your teammates or keep them personal.

  • Dashboard

    Pro-rata usage quota, current AI agents, queued AI tasks, queue of required reviews, "hot" tickets, and more.

  • Notifications

    Get browser and/or Discord notifications when AI is finished or needs you.

  • Claude web bridge

    Orchestrate agents via Claude Code Web for 0% local CPU usage.

  • Swarm of local computers

    Orchestrate agents across multiple local computers.

  • Discord bot

    Use the discord bot for agentic team conversations.

Your framework

It isn't our framework. It's yours.

Flexible

  • OpenAgent doesn't force anything — pick only the features you need
  • Coming soon Customize anything to fit your needs

100% Local

  • Runs locally on your machine, like a desktop app
  • No backdoors, no tracking
  • Memory is saved in your Git repository at knowledge-base/*.md
  • Data is fully yours

100% Open Source

  • Transparent — no hidden code
  • Something's not working for you? Ask your favorite AI to make a Pull Request — we welcome agentic contributions!

Join our community of agentic developers

Join us on DiscordStar on GitHub