#7474th of 87 in Coding agents and assistants

omnirush-gui

Desktop coding agent app for macOS and Linux with a model picker

Stars: 3.4k
License: custom license
Last commit: Oct 2026
Last release: Oct 2026
Language: TypeScript

Missed the latest GitHub check; these facts may be older.

Overview

Electron-style desktop app that runs a coding agent against your local projects. It clones repos, branches, commits, pushes and opens or reviews pull requests through `gh`, with approval prompts for write and destructive commands. Prompts run only after signing in to an omnirush.ai account, though you can add your own OpenAI, Anthropic or other provider keys.

Who it is for: Developers wanting a desktop GUI coding agent on macOS or Linux

Strengths

Per-chat model and effort selection (low, high, xhigh, max)
Skills and MCP servers added from a Library in Settings, shared across models
Git workflow support with approval prompts; destructive commands always ask
Packages for macOS arm64 and Linux x64/arm64 (deb, rpm, pacman, AppImage, tar.gz)

Weaknesses

Requires an omnirush.ai account sign-in before any prompt runs
No build for Intel Macs or Windows
macOS builds are not notarized; first launch needs a manual override
License detected as NOASSERTION; README cites MIT with a separate ee/ license

What it needs

no GPU
Needs omnirush.ai account, gh CLI (for pull request workflows), GTK runtime libraries (AppImage/tar.gz on Linux)
Models: GPT 6 Astra, GPT 6.1 Sol, OpenAI (own key), Anthropic (own key)

Also in Coding agents and assistants

See all 87

Also in Coding agents and assistants
Rank	Project	Score
1	claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs194.9k starsMIT	83 out of 100
2	ArchonYAML workflow engine that runs AI coding agents through fixed dev steps23.7k starsMIT	82 out of 100
3	oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory70.1k starscustom license	80 out of 100
#4	Open SWELangChain coding agent that plans, implements and reviews pull requests11k starsMIT	80 out of 100
#5	opencodeTerminal coding agent with build and plan modes, plus a desktop app213.8k starsMIT	79 out of 100

How to choose

Check which models it can use: your own keys, local models, or only the vendor's.
See what it may do without asking (edit files, run shell, push) and how you approve.
Prefer agents that work in a branch or worktree you can throw away.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

custom license Custom terms

Use it at work: Check
Change it and rebrand it: Check
Sell it or host it for others: Check

Your part: GitHub could not match these terms to a standard license. Read the license before you use it at work, rebrand it or host it for others.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#74 of 87 in Coding agents and assistants on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/omnirush-ai/omnirush-gui.svg)](https://archestack.com/best-of-vibe-coding/projects/omnirush-gui/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/omnirush-gui/" title="omnirush-gui on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with omnirush-gui filled in.