back to top
HomeSoftwareMiniCPM Desk Pet: Open Source AI Desktop Companion That Runs Locally

MiniCPM Desk Pet: Open Source AI Desktop Companion That Runs Locally

- Advertisement -

File Info

FileDetails
NameMiniCPM Desk Pet
Versionv0.7.3
DeveloperOpenBMB Community & Contributors
LicenseAGPL-3.0 Licene (Open Source)
PlatformmacOS, Windows
ArchitectureApple Silicon (ARM64), Windows x64
Files.dmg, .exe
GitHub RepositoryMiniCPM Desk Pet

Description

MiniCPM Desk Pet turns the MiniCPM AI model into a desktop companion that lives alongside your workflow. Install the app, follow the setup wizard, and within a few minutes you can chat with a local AI pet directly from a floating desktop bubble.

The app checks your environment, downloads the model, warms it up, and simplify the complexity of the setup

Once everything is ready, conversations run on your machine using the local model. The pet can stay visible while you work, react to activity from tools like Cursor, Claude Code, and Codex, and even take on different personalities through character adapters.

It’s part local AI assistant, part desktop pet.

Use cases

  • Chat with a local AI model without relying on cloud inference
  • Keep a lightweight AI assistant available while coding
  • Add a desktop companion that reacts to development workflows
  • Experiment with MiniCPM and persona adapters

Screenshots

Features of MiniCPM Desk Pet

FeatureDescription
Local AI ChatRun conversations locally after model setup
Desktop Pet InterfaceFloating companion that stays on screen while you work
Guided SetupAutomatic environment check, model download, and warm-up
Agent Activity ReactionsResponds to activity from Cursor, Claude Code, and Codex
Smart Model DownloadsDownloads from Hugging Face or ModelScope automatically
Persona SupportSwitch or import different character adapters
Local Model ManagementChoose custom GGUF models and manage runtimes
Keyboard ShortcutsQuick access to chat and thinking mode
Cross-Platform SupportAvailable for macOS and Windows
You May Like: OpenHuman: Open-Source Personal AI Assistant With Memory, Voice & Integrations

System Requirements

ComponentRequirement
macOSmacOS 14+
Windowsx64 with Vulkan support
ProcessorApple Silicon (M1/M2/M3/M4) or modern x64 CPU
StorageApproximately 2 GB
NetworkRequired during first setup or model download

How to Install MiniCPM Desk Pet?

Windows

  1. Download the .exe file.
  2. Run the installer.
  3. Complete the installation wizard.
  4. Launch the application.
  5. Follow the setup guide to download and initialize the model.

On first launch, the app walk through the environment check, then it will download the Model, Warm-Up the model and then You can use the application

macOS

  1. Download the .dmg release.
  2. Open the DMG file.
  3. Drag MiniCPM Desk Pet into the Applications folder.
  4. Launch the application.
  5. Follow the guided setup process.
Discover More Open Source AI tools for your system

Download MiniCPM Desk Pet

An AI Desktop Pet and Assistant

If you like the idea of having an AI assistant nearby throughout the day, without relying on a cloud service for every conversation, you can give this project a try. The setup is simple, the model runs on your own machine, and the desktop pet approach makes it feel different from the usual chatbot experience.

Don’t miss any Tech Story

Subscribe To Firethering NewsLetter

You Can Unsubscribe Anytime! Read more in our privacy policy

LEAVE A REPLY

Please enter your comment!
Please enter your name here

YOU MAY ALSO LIKE
brew-browser Native Homebrew GUI for macOS to Manage Packages, Services & Brewfiles

brew-browser: Native Homebrew GUI for macOS to Manage Packages, Services & Brewfiles

0
brew-browser doesn't replace Homebrew. It simply gives it a proper macOS interface. You can see what's installed, search thousands of packages, upgrade software, manage services, and create Brewfile snapshots without memorizing commands or keeping multiple terminal windows open. Everything still runs through the real brew CLI, so you're not learning a new package manager or dealing with a compatibility layer. It can pull information into one place. Installed packages, available updates, storage usage, trending Homebrew packages, services, snapshots, and even optional vulnerability scanning all live inside a native desktop app that feels at home on macOS.
Donut Browser Open Source Anti-Detect Browser With Unlimited Isolated Profiles

Donut Browser: Open Source Anti-Detect Browser With Unlimited Isolated Profiles

0
If you've ever managed multiple accounts in the same browser, you've probably run into the usual mess. Wrong account logged in. Cookies bleeding between sessions and more. Donut solves that by treating every profile as its own browser. Create a profile, attach a proxy if you want, and it gets its own cookies, storage, extensions, fingerprint, and network settings. Open five profiles and it feels like you're using five separate browsers. Everything stays local. There's no account to create. You download the app, create profiles, and get on with your work. If you're managing client accounts, testing websites, keeping work and personal browsing apart, or building automation workflows through the local API, Donut gives you a clean way to keep identities separated without turning your browser into a headache.
Maya Open Source macOS App for Creating Cinematic iPhone Screen Recording Videos

Maya: Open Source macOS App for Creating Cinematic iPhone Screen Recording Videos

0
Drop in a .mp4 or .mov screen recording, pick an iPhone frame, add a few zoom moments on the timeline, and export a clean clip for Reels, TikTok, Shorts, product demos, or in-app tutorials. Maya keeps the workflow simple: frame the recording, tweak the motion, hit export. You can render a regular H.264 .mp4 for social platforms or export a transparent HEVC .mov with alpha for overlays inside apps, presentations, or video editors. The app runs natively on macOS. It ships with iPhone 17, 16, and 15 Pro frames, background presets, animation curves, timeline editing, and one-click zoom presets that make raw screen recordings feel a lot less raw.