# omnirush-ai/omnirush-gui

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/omnirush-ai-omnirush-gui).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,876 stars · 140 forks · TypeScript · NOASSERTION

## Links

- GitHub: https://github.com/omnirush-ai/omnirush-gui
- Homepage: https://omnirush.ai
- awesome-repositories: https://awesome-repositories.com/repository/omnirush-ai-omnirush-gui.md

## Description

Omnirush GUI is a desktop application that runs an AI coding agent against files on a person's own machine, along with Git repositories and a web browser. Each chat can use its own model and reasoning effort level, chosen from the models available in the connected account. Local data stays local by default, with optional cloud use. Git and GitHub tasks such as cloning, branching, committing, pushing and opening pull requests can be run from chat, including parallel branches through separate worktrees.

The project puts heavy emphasis on controlling what the agent may do. Shell commands are classified by risk tier, with read-only commands running freely and riskier ones prompting for approval. Destructive actions such as force pushes, hard resets and recursive deletes always ask first. Users can switch between a guarded mode and a full-permissions mode, and organization-defined deny rules take precedence over either. Freshly opened projects are blocked from running their own plugins, tools and language servers by default, and an optional Linux sandbox keeps agent-driven builds and tests off the user's machine.

Around the desktop client sits an organization layer. A central control plane provisions inference, manages teams and access, and applies policies to every installation. Skills and plugins can be distributed through marketplaces so members receive only approved capabilities, and a single MCP endpoint exposes those assigned capabilities to compatible clients such as Codex, Claude Code and Cursor. Automated security review runs on pull requests and uncommitted local changes, withholding approval while blocking findings remain and scanning for confidential identity leaks.

The repository also covers its own delivery and testing. It builds installers for macOS (Apple Silicon and Intel), Windows and Linux, publishes tagged releases, and delivers checksum-verified in-app updates with rollback to earlier releases. End-to-end tests run in reproducible local or cloud sandboxes and capture screenshots and recordings as evidence of passing behavior.

## Tags

### Artificial Intelligence & ML

- [Desktop AI Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/desktop-ai-agents.md) — Desktop application running an AI coding agent against local files, Git repositories and a web browser, with per-chat model and effort selection.
- [Tool Execution Approvals](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-action-frameworks/action-approval-gates/tool-execution-approvals.md) — Asks for user confirmation before risky agent tool calls, always prompts on destructive actions, and blocks untrusted project code from running by default.
- [Local File Chat Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-application-frameworks/local-on-device-ai/local-chat-analysis-agents/local-file-chat-agents.md) — Runs an AI agent against files on the user's own machine, keeping data local by default with optional cloud use. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/AGENTS.md))
- [Skill Installation](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-skill-frameworks/skill-installation.md) — Installs reusable skills from a built-in library in settings so every available model sees the same installed skills. ([source](https://github.com/omnirush-ai/omnirush-gui#readme))
- [Reasoning Effort Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-reasoning-engines/reasoning-effort-configurations.md) — Lets each chat pick its own model from the connected account and set a reasoning effort level. ([source](https://github.com/omnirush-ai/omnirush-gui#readme))
- [Per-Chat Model Selection](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-reasoning-engines/reasoning-effort-configurations/per-chat-model-selection.md) — Lets each chat use its own model from the connected account and its own low, high, xhigh or max reasoning effort level. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/README.md))
- [Action Approval Gates](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-action-frameworks/action-approval-gates.md) — Always asks for approval before destructive actions such as force pushes, hard resets, branch deletions, and recursive deletes, even when nested in wrappers or subshells. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/git-workflows.md))
- [Skill Marketplaces](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-skills/skill-marketplaces.md) — Distributes curated skills and plugins through organization marketplaces so members receive only approved capabilities. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/AGENTS.md))
- [Browser Automation Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/browser-automation-agents.md) — Lets an AI agent drive a web browser through multi-step tasks on a person's behalf from the desktop workspace. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/AGENTS.md))
- [MCP Capability Management](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-capability-management.md) — Exposes assigned skills, plugins and connections through one MCP endpoint that clients like Codex, Claude Code and Cursor can call. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/AGENTS.md))
- [MCP Gateways](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-gateway-federations/mcp-gateways.md) — Offers a single MCP endpoint exposing assigned skills, plugins and connections so compatible clients can discover and call them.

### Development Tools & Productivity

- [Agent Action Approval Policies](https://awesome-repositories.com/f/development-tools-productivity/ai-coding-assistants/agent-action-approval-policies.md) — Controls what the agent may run by asking before risky commands, always prompting on destructive actions, and blocking untrusted project code by default.
- [Chat-Driven Git and GitHub Operations](https://awesome-repositories.com/f/development-tools-productivity/chat-driven-git-and-github-operations.md) — Runs cloning, branching, worktrees, commits, pushes, and pull request creation or review with git and gh directly from the chat. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/git-workflows.md))
- [Team Management](https://awesome-repositories.com/f/development-tools-productivity/team-management.md) — Manages teams, access and desktop policies from one central control plane that applies to every desktop installation. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/AGENTS.md))
- [Agent Sandboxes](https://awesome-repositories.com/f/development-tools-productivity/agent-sandboxes.md) — Offers an optional Linux sandbox that keeps agent-driven builds, tests, and tool servers off the user's machine. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/skills-and-mcp.md))
- [Agentic Plugin Marketplaces](https://awesome-repositories.com/f/development-tools-productivity/agentic-plugin-marketplaces.md) — Distributes curated skills and plugins through marketplaces so organization members receive only approved agent capabilities.
- [Automated Pull Request Reviewers](https://awesome-repositories.com/f/development-tools-productivity/developer-utilities-libraries/developer-tools/version-control-ecosystems/github-integrations/automated-pull-request-reviewers.md) — Automatically reviews pull requests and uncommitted diffs for security issues and identity leaks, blocking approval while findings remain.
- [Pull Request Review Interfaces](https://awesome-repositories.com/f/development-tools-productivity/pull-request-review-interfaces.md) — Runs automated security review on pull requests and local changes, withholding approval while blocking findings remain and scanning for confidential identity leaks.
- [Sandboxed Shell Executions](https://awesome-repositories.com/f/development-tools-productivity/shell-command-execution/sandboxed-shell-executions.md) — Optional Linux sandbox runs agent-driven builds, tests and tool servers off the user's machine, with risk-tiered approvals for shell commands.

### Security & Cryptography

- [Command Risk Classification](https://awesome-repositories.com/f/security-cryptography/command-risk-classification.md) — Classifies every shell command segment as read-only, write, destructive, or interpreter, running safe ones freely and prompting before riskier ones. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/git-workflows.md))
- [Agent Tool Permissions](https://awesome-repositories.com/f/security-cryptography/security-and-access-control/agent-tool-permissions.md) — Asks permission before write or destructive agent actions and offers a full-permissions toggle that switches between prompting and automatically allowing every tool call. ([source](https://github.com/omnirush-ai/omnirush-gui#readme))
- [Approval Mode Switching](https://awesome-repositories.com/f/security-cryptography/approval-mode-switching.md) — Lets users switch between guarded mode that prompts on risky tool calls and full-permissions mode, reloading the engine so new rules apply within seconds. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/approvals.md))
- [Automated Diff Security Reviews](https://awesome-repositories.com/f/security-cryptography/automated-diff-security-reviews.md) — Runs automated security review on every pull request and on uncommitted local changes, withholding approval while blocking findings remain. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/warden.toml))
- [Merge Approval Gating](https://awesome-repositories.com/f/security-cryptography/finding-classification/merge-approval-gating.md) — Withholds pull request approval while blocking findings remain, treats lower-severity findings as advisory, and double-checks results with a strong model. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/warden.toml))
- [Central Access Policies](https://awesome-repositories.com/f/security-cryptography/policy-based-access-control/central-access-policies.md) — Applies organization-wide deny rules and command policies centrally so every desktop installation follows the same restrictions and approved capabilities.
- [Organization Policy Overrides](https://awesome-repositories.com/f/security-cryptography/role-based-access-control/conditional-access-rules/explicit-deny-rules/organization-policy-overrides.md) — Applies organization deny rules, blocked commands, and approved browser origins on top of approval modes so a deny always wins, even in full-permissions mode. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/approvals.md))
- [Organization Command Deny Rules](https://awesome-repositories.com/f/security-cryptography/security/policies/host-resource-access/file-system-access-controls/path-access-restrictions/path-access-restrictions/default-deny-policies/organization-command-deny-rules.md) — Appends organization-defined deny and blocked-command rules after the defaults so an organizational restriction always overrides any local or remembered approval. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/git-workflows.md))
- [Untrusted Project Code Blocking](https://awesome-repositories.com/f/security-cryptography/untrusted-project-code-blocking.md) — Blocks a freshly opened project from running its own plugins, custom tools, language servers and formatters by default, showing a notice of what was skipped. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/skills-and-mcp.md))

### DevOps & Infrastructure

- [Desktop App Packaging and Auto-Updates](https://awesome-repositories.com/f/devops-infrastructure/desktop-app-packaging-and-auto-updates.md) — Builds installers for macOS, Windows and Linux, publishes tagged releases, and delivers checksum-verified in-app updates with rollback to earlier versions.
- [Cross-Platform Installations](https://awesome-repositories.com/f/devops-infrastructure/distribution-packaging/software-distribution/native-installers/windows-installers/cross-platform-installations.md) — Produces installers and archives for macOS on Apple Silicon and Intel, Windows and Linux, each built independently within one release. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/RELEASING.md))
- [Tag-Triggered Release Automators](https://awesome-repositories.com/f/devops-infrastructure/release-automation/git-release-automators/tag-triggered-release-automators.md) — Triggers an automated workflow from a semantic-version tag to build installers per platform, generate checksums, and publish only after every build succeeds. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/docs/RELEASING.md))

### Software Engineering & Architecture

- [Centralized Policy Administration](https://awesome-repositories.com/f/software-engineering-architecture/centralized-policy-administration.md) — Central control plane that provisions inference, manages teams and access, and enforces approval and command policies on every desktop installation.
- [Agent Skill Extenders](https://awesome-repositories.com/f/software-engineering-architecture/integration-extensibility/extensibility/plugin-architectures/developer-authoring-interfaces/custom-module-implementations/module-functionality-extenders/plugin-extenders/agent-skill-extenders.md) — Adds reusable skills and compatible plugins that give agents new abilities and task-specific workflows inside the desktop app. ([source](https://github.com/omnirush-ai/omnirush-gui/blob/main/AGENTS.md))
