What can I use Cindy for?

Send Cindy a task from a chat app while you are away, and it does the work on your own computer using your real files; Give Cindy a task in your project and have it planned, worked on in parallel by agents on different models, then checked by a reviewing agent; Ask Cindy to drive your browser or phone to carry out a task in an app you are already logged in to

What do I need to use Cindy?

Download the app from the project's Download page (macOS, Windows or Linux). Reach models with a Cindy sign-in, a Claude Code or Codex plan you already have, your own API keys, or local models; Skip Sign-In runs local agents without an account. Building from source instead needs Node.js 22.x, pnpm 10.x and Git LFS.

Cindy: Let an AI agent finish tasks in your apps and files

What it does

Cindy is a desktop and mobile app that joins several agent harnesses (the programs that let an AI model take actions, starting with Claude Code and Codex) with models and tools. You can switch models mid-task while memory, skills and tools carry over. It can drive your browser, computer and phone, and take work from chat apps and schedules.

How to use it

Download the app from the Download page and open it. Then sign in to the Cindy service, connect a Claude Code or Codex plan you already pay for, add your own API keys, or use local models; choosing Skip Sign-In on the login screen runs local agents without a Cindy account.

Common use cases

Send Cindy a task from a chat app while you are away, and it does the work on your own computer using your real files.
Give Cindy a task in your project and have it planned, worked on in parallel by agents on different models, then checked by a reviewing agent.
Ask Cindy to drive your browser or phone to carry out a task in an app you are already logged in to.

Can I use this?

Mac, Windows or Linux app

Requirements App downloads are published for macOS, Windows and Linux; Linux users should follow docs/linux.md. Hardware requirements are not documented.

Caveat The client is open source under Apache-2.0; a hosted Cindy service with separate pricing also exists, and server-backed features are unavailable without sign-in. Team skill sharing and the plugin marketplace are still being built.

Worth knowing Skipping sign-in runs local agents, but server-backed features become unavailable. The backend service is not in this repository. Licensed under Apache License 2.0.

Why it's here

Not trending this week

Last seen on the GitHub trending list on 4 November 2026. It stays on BuildTube so you can still find it.

9,505 people have starred it on GitHub.

Numbers checked on 8 November 2026; not refreshed since.

Behind it

View setup guide

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?

Quick questions

What is Cindy?: Cindy is a desktop and mobile app that joins several agent harnesses (the programs that let an AI model take actions, starting with Claude Code and Codex) with models and tools.
What can I use Cindy for?: Send Cindy a task from a chat app while you are away, and it does the work on your own computer using your real files; Give Cindy a task in your project and have it planned, worked on in parallel by agents on different models, then checked by a reviewing agent; Ask Cindy to drive your browser or phone to carry out a task in an app you are already logged in to
Can I run Cindy on my computer?: It installs as a desktop app on your own computer. App downloads are published for macOS, Windows and Linux; Linux users should follow docs/linux.md. Hardware requirements are not documented.
What do I need to use Cindy?: Download the app from the project's Download page (macOS, Windows or Linux). Reach models with a Cindy sign-in, a Claude Code or Codex plan you already have, your own API keys, or local models; Skip Sign-In runs local agents without an account. Building from source instead needs Node.js 22.x, pnpm 10.x and Git LFS.
What license does Cindy use?: Licensed under Apache License 2.0.

More from this week

Stroq Check AI coding agent sessions for leaked keys
Stroq scans your recent Claude Code and Codex sessions for keys that left your machine.
Runs in a terminalAdded 6 Nov
agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
+13,858 stars this weekAdded 3 Nov
kimi-k3-in-c Run a 2.78-trillion-parameter model on 8 GB of RAM
Get text answers from the huge Kimi K3 AI model using one CPU and no graphics card.
+1,920 stars this weekAdded 4 Nov

Related projects

OpenMausBot Chat with a team of AI bots that use computers
Same topic: claude-code
+7,077 stars this weekDesktop appAdded 31 Oct
oh-my-hermes Add planning and evidence rules on top of the Hermes agent
Same topic: agent
Runs in a terminalAdded 20 Sept
Headroom Shrink what your AI agent reads so it uses fewer tokens
Same topic: agent
Needs a local setupAdded 21 Oct
RustDesk Control another computer remotely without a company in between
Same topic: android
Needs a local setupAdded 11 Oct
Cua Give an AI agent a whole computer to operate, in a sandbox
Same topic: agent
Runs in a terminalAdded 25 Sept
Graphify Map a codebase and its docs into a graph you can query
Same topic: claude-code
+4,147 stars this weekAdded 19 Oct

Explore by topic

Post this

For makers

Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.

README badge (Markdown)

[![Featured on BuildTube](https://buildtube.app/badge/gh-makecindy-cindy.svg)](https://buildtube.app/p/gh-makecindy-cindy/)

Embed card (HTML)

<iframe src="https://buildtube.app/embed/gh-makecindy-cindy/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="Cindy on BuildTube"></iframe>