A Windows desktop home for local AI coding - run models on your own machine through Ollama, with no API keys.
MandoCode Desktop is a Windows desktop app for local AI coding. Run models on your own hardware through Ollama (or cloud models with an ollama.com subscription), with multi-agent tabs, session persistence, context snapshots, MCP server support, file tagging, diff approvals for every write, and themes. Self-contained - no .NET installation required.
| Publisher | DevMando |
|---|---|
| Version | 0.14.1 |
| Release date | 2026-07-28 |
| License | MIT |
| Installer type | zip |
| Architecture | x64 |
| Package ID | DevMando.MandoCode.Desktop |
| Requirements | Windows 10 version 2004 or later |
winget install --id=DevMando.MandoCode.Desktop -ewinget upgrade --id=DevMando.MandoCode.Desktop -ewinget uninstall --id=DevMando.MandoCode.Desktop -eYes. MandoCode Desktop is free and open-source software released under the MIT license.
The latest version is 0.14.1, released on Jul 28, 2026.
The download button links to the official installer published on github.com, the same file Windows Package Manager installs. You can verify the downloaded file by comparing its SHA-256 checksum with 02eb65aace3fc7f9cfcb2621b20894a01700afc4a83ff309bc6377cea0096855.
MandoCode Desktop requires Windows 10 version 2004 or later and is available for 64-bit (x64) systems.
Open Settings › Apps › Installed apps, find MandoCode Desktop and select Uninstall. From the command line, run winget uninstall --id=DevMando.MandoCode.Desktop -e.
Yes. MandoCode Desktop is available as a portable ZIP archive (MandoCode.Desktop-v0.14.1-win-x64.zip, 64-bit (x64)) that runs without installation. Copy it to any folder or USB drive and run it from there.
Other AI for Productivity programs for Windows from different developers.
Agent Supervisor & Model Dispatcher for coding agents (spicebox.dev/nacho-flow).
An open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities.
A desktop LLM client with magical MCP support
Effortlessly run LLM backends, APIs, frontends, and services with one command.
Refreshingly fast LLMs on GPUs and NPUs.
A desktop launcher for running several AI coding agents side by side.