orke

A desktop workspace for coding agents, browser review, and Git

orke brings AI coding-agent terminals, a browser view, and Git controls into one desktop workspace. You can hand work to tools such as Claude Code and Codex, review their changes, and continue the same session remotely from a phone or Linux server.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 18 October 2026.

iOS

Desktop

Code Execution

Web Browsing

B2B

Computer Use

Visit orke

Is this your tool? Claim this listing to manage your content and analytics.

Ask about orke

Get answers based on orke's actual documentation

Try asking:

About

What It Is

orke is a desktop workspace for developers using terminal-based AI agents, including Claude Code and Codex. It connects an agent terminal with an in-app web view and Git interface, so you can direct an agent to change code, inspect the resulting...

What to Know

The strongest use case is a developer workflow where the agent can make changes in a local project and you need a single place to review both the live result and the Git diff. Its request-to-work-to-review-to-commit flow keeps a human in control of...

Key Features

Runs AI-agent sessions in an integrated terminal workspace

Connects Claude Code, Codex, OpenCode, Hermes, and Antigravity CLI workflows

Pairs agent work with an in-app browser view for reviewing page changes

Lets you select a page element and send an instruction to the agent working on it

Provides Git status, diffs, staging, commit, branch, remote, and stash controls

Use Cases

Ask a coding agent to update a local web app, then review the changed page and Git diff before committing

Use a browser-page selection to give an agent targeted UI-change instructions

Monitor a long-running coding session from a phone after starting it on a PC

Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence

Last evaluated: Oct 18, 2026

Dimension Breakdown

Action Capability

Planning

Adaptation

State & Memory

Reliability

Interoperability

Safety

Operator Sovereignty

How agenticness works →

When orke changes its pricing, we catch it the next morning

We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.

Similar tools

Related Tools

See all Coding Agents tools compared

Kilo Code

Agenticness14/36·Adaptive Collaborator

Coding Agents

Kilo Code is the v5.x community fork of Roo Code (which was archived May 15, 2026). Open-source VS Code extension for agentic coding — Apache 2.0 licensed, BYOK across many providers, runs locally as an IDE extension.

OpenHands

Agenticness18/36·Adaptive Collaborator

Coding Agents

OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).

Augment Code

Agenticness14/36·Adaptive Collaborator

Coding Agents

Augment Code is an enterprise-focused AI coding agent built around a 200K-token Context Engine. Closed-source SaaS with strong SWE-bench Verified results (70.6% self-reported) and the highest accuracy on the only public benchmark for AI-assisted code review.

Orbi

Agenticness22/36·Domain Specialist

Coding Agents

Orbi is an open-source, self-hostable AI coding agent that takes GitHub Issues from implementation through independent review, merge, and release. It can run against your own model endpoint or through Orbi’s managed cloud service.

Desktop

Code Execution

Integrations

Ask about orke

About

Dimension Breakdown

Categories

Ask about orke

When orke changes its pricing, we catch it the next morning

Related Tools