omnirush-ai/omnirush-gui

A desktop coding agent with free access to frontier models.

View on GitHub ↗Jump to charts ↓

omnirush-ai/omnirush-gui has 3.5k+ stars and 80+ forks on GitHub, is written in TypeScript, and was last pushed on Oct 18, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 1 hour ago
Type:ApplicationCategory(s):AI Coding AgentsAI Agents & LLM Apps
Added to GitGenius on October 9th, 2026
Created on September 21st, 2026
Open Issues & Pull Requests: 27 (+0)
GitHub issues: Enabled
Number of forks: 89
Total Stargazers: 3,599 (+2)
Total Subscribers: 23 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 0.0 hours
Mean response time: 0.0 hours
90th percentile: 0.0 hours
Tracked items: 1

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 12
New in 7 days: 6
Closed in 7 days: 0
Avg open age: 3 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 5
Closed in 7 days: 0
Comments in 7 days: 5
Events in 7 days: 6

Top labels

  • bug (4)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Omnirush is a desktop coding agent that provides free access to frontier models.

The tool addresses the need for developers to work with AI coding assistance directly within their own projects without subscription costs. It operates as a desktop application that integrates a coding agent with access to multiple language models, with GPT 6 Astra as the default option and other models available through a model picker interface. The agent can be directed to work on code within a user's local environment.

Developers should consider this tool if they want an AI coding assistant without ongoing subscription fees and prefer a desktop application over web-based alternatives. It supports macOS with Apple Silicon processors and Linux systems across both x64 and arm64 architectures, making it accessible to developers on those platforms. The project also offers a command-line interface through an npm package for those preferring terminal-based workflows.

The project maintains active release cycles with versioned builds distributed across multiple Linux package formats and macOS installers, indicating ongoing development and platform support. Releases include SHA256 checksums for download verification, suggesting attention to security practices. The availability of both graphical and command-line interfaces indicates the maintainers are building for different user preferences and workflows.