MCP server
makecindy / cindy
Consider it done. The open-source AI agent that works out of the box · 想到,就能做到。开源、开箱即用的 AI Agent。
This connects Repowise to makecindy/cindy's code. It does not install cindy.
Repowise maps public repos from their source. Not affiliated with makecindy. What is Repowise?
github.com/makecindy/cindyIndexed at 82d44ec
What is cindy?
Cindy is an open-source AI agent meant to finish real work in your projects and apps. It runs on your own machine using your local files and logged-in apps, and it brings multiple harnesses, models and tools into one agent. This repository holds the open-source client, which includes a desktop app, a mobile app and shared packages, written mainly in TypeScript. To install it, run git clone https://github.com/makecindy/cindy.git and follow the steps below. Its code health is 6.5 out of 10 (Fair), ranked #185 of 4,000+ indexed repos. The last commit to cindy was on Oct 27, 2026, and 173 people have contributed.
As of commit 82d44ec, indexed Oct 27, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.
For agentscindy.md
Repo facts: type, license, health, rank, contributors
| Type | MCP server |
|---|---|
| License | Apache-2.0 |
| Code health | 6.5 / 10 (Fair) |
| Health rank | #185 of 4,000+ indexed repos |
| Last commit | Oct 27, 2026 |
| Contributors | 173 |
| Bus factor | 2 |
| Size | 15,969 files, 3,431,342 lines |
Install cindy
Commands copied from the README
- 1Clone the cindy repository.
git clone https://github.com/makecindy/cindy.git - 2Move into the cindy folder.
cd cindy - 3Pull the Git LFS files in the repository
git lfs pull - 4Install the dependencies with pnpm
pnpm install - 5Start the desktop app for a Mainland China Cindy account
pnpm restart:desktop:remote --region=cn
Releases on GitHub (latest v0.1.143, Nov 20, 2026)
Explore cindy
- DocumentationModule-by-module documentation, 9,336 pages.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score and the findings behind it.
- CommitsEach commit's effect on code health.
- OverviewEverything else the index found: contributors, decisions, what changed this week.
Ask about this code in your agent
This connects Repowise to cindy's code. It does not install cindy. To install cindy, use the install steps.
Useful if you want to change or fork cindy: your agent can ask how it is put together and get answers that cite its files.
Ask about cindy
Answers come from cindy's README and source, with the files they cite. Two free answers a day without an account.
Want this for your own codebase? Map your repo free
About this page
Get a page like this for your own codebase
Repowise built this map of makecindy/cindy from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.
Free for 2 public repos, with a page like this one. No card. See how Repowise works
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub
makecindy/cindy FAQ
What is Cindy?
Cindy is an open-source AI agent that works out of the box on your own machine. This repository is its open-source client, made up of desktop and mobile apps and shared packages organized as a pnpm monorepo.
How does Cindy work?
Cindy brings multiple harnesses, models and tools into one agent. The first supported harnesses are Claude Code and Codex, and models can switch mid-task while the workspace, memory, skills and tools stay continuous.
How do I install Cindy?
Cindy needs Node.js 22.x, pnpm 10.x and Git LFS. Clone the repository, run git lfs pull, then run pnpm install in the repository folder. See the install steps
What language is Cindy written in?
Cindy is written mainly in TypeScript. JavaScript, Swift, Python, Rust and Kotlin files are also present in the repository.
How is the Cindy code organized?
The repository is a pnpm monorepo. apps/desktop holds the Electron desktop client, apps/mobile holds the React Native mobile client, and packages/* holds shared client capabilities.
Who is Cindy for?
Cindy is for people who want an AI agent that finishes real work in their projects and apps. It can also drive a browser, computer and phone and take work from IM and schedules.
What license does Cindy use?
Cindy uses the Apache-2.0 license. Its client source code is open under that license, so you can audit, fork, extend and contribute improvements back.
Code health
Hotspots average 5.2, the place fixes pay off most.
On the leaderboards:#60 of 70 TypeScript repos
Key features of cindy
- Runs locally on your own machine using your real files and logged-in apps.
- Mixes models and harnesses, and can switch between them mid-task while workspace, memory, skills and tools stay continuous.
- Stores memory that is shared across harnesses, so corrections carry over to later work.
- Lets you teach reusable skills and schedule recurring work through automation.
- Connects internal tools and business systems through MCP.
- Source is open under Apache-2.0, so it can be audited, forked, extended and contributed to.
How makecindy/cindy works
Input reaches the client as user prompts, IM channel messages, and account and device state, and the desktop app, mobile app and headless CLI are the surfaces people use. apps/desktop is the Electron client that runs on a user's own machine, handling clicks, local files and messages from cloud and device peers. apps/mobile is a React Native client for phones that reshapes session and remote-device data for its screens. packages/lizi-im gives the desktop app one way to talk to chat platforms such as Feishu, Telegram and Discord, sending replies and files back out. packages/lizi-mcps builds the in-process MCP servers that give desktop agents their tools, each with its own tool list. apps/cindy-headless/src/cli.ts is the entry point for the headless command line interface.
The codebase has 15,969 files and 115,624 symbols in 5 modules, led by TypeScript, JavaScript and Swift. Code health is 6.5 out of 10, rated fair.
Maintain makecindy/cindy?
Claim this page, add a badge to the README, or re-index it.
Claim this page
Sign in with GitHub and we check that you are an admin or maintainer of makecindy/cindy. Then add a badge to the README that links readers here.
Add a badge to your README
Readers click through to this page and can ask cindy's code a question. A badge also re-indexes the repo every week and marks you as the verified maintainer.
[](https://repowise.dev/repo/makecindy/cindy?src=badge_ask)Paste it at the top of README.md, under the title.
Added it already? Verify to get the mark now instead of tomorrow.
Need HTML or the larger health card? More formatsHide more formats
This badge as HTML
<a href="https://repowise.dev/repo/makecindy/cindy?src=badge_ask"><img src="https://api.repowise.dev/badge/wiki/makecindy/cindy.svg?label=ask" alt="repowise: Ask this codebase"></a>Code health card
The score, its change since the last index, and when it was measured. Follows the reader's light or dark theme.
<a href="https://repowise.dev/repo/makecindy/cindy?src=badge_card"><picture><source media="(prefers-color-scheme: light)" srcset="https://api.repowise.dev/badge/health/makecindy/cindy.svg?style=card&theme=light"><img src="https://api.repowise.dev/badge/health/makecindy/cindy.svg?style=card" alt="repowise code health" width="500" height="168"></picture></a>