Ronin / capability
Use the agents you already trust.
Connect the CLIs already installed on your machine. Switch provider, account, model, and reasoning effort without changing the shape of your workflow.
Bring your coding agents, terminal, browser, diffs, and source control together in one local-first desktop workspace.

Why Ronin
Coding agents are powerful in a terminal. They become practical when you can see the work, set the limits, compare the changes, and ship with intent. Ronin gives that loop a focused interface.
Core system
Ronin / capability
Connect the CLIs already installed on your machine. Switch provider, account, model, and reasoning effort without changing the shape of your workflow.
Ronin / capability
Choose Supervised, Auto-accept edits, Auto, or Full access before the work begins. Approvals appear inline when the agent reaches a boundary.
Ronin / capability
Review diffs, restore a checkpoint, isolate work in a worktree, commit, push, and open the pull request without losing the thread.
Ronin / capability
Provider processes, terminals, filesystem reads, and git operations run on the server you control. Connect over LAN, Tailscale, or SSH when you need distance.
The product
The primary object is a thread with a repository behind it. Everything else— terminal, browser, usage, diff, and source control—stays close enough to act on.
Workspace
Compose with any connected agent, choose its model and autonomy, then keep the terminal, preview, diff, and git state in the same working context.

Working loop
From intent to merge
Every turn has a visible state. Every change can be inspected. Every branch can stay isolated. You decide when the result is ready to leave the machine.
Give the agent the repo, model, effort, and permission boundary.
Watch commands, edits, terminal output, and browser actions arrive in context.
Read the latest-turn diff, leave line comments, or restore a checkpoint.
Commit, push, and open the pull request from the workspace header.
Browser preview / MCP
Ronin exposes fourteen focused browser tools to the active agent—navigation, interaction, snapshots, appearance control, and recording—against your real dev server.
preview_openpreview_clickpreview_typepreview_snapshotpreview_recording_startStraight answers
Ronin is an open-source desktop harness for coding agents. It runs the provider CLIs already installed on your machine and gives their threads a shared interface for prompts, permissions, terminal output, browser previews, diffs, usage, and source control.
No. Ronin is an agent harness, not a text editor. The primary object is the thread and its repository context. It opens files and shows diffs when useful, then hands focused editing back to the editor you already use.
Ronin is free and MIT-licensed. It does not resell models, tokens, or subscriptions. You install and authenticate the supported provider CLIs yourself.
Ronin's execution layer is local: provider processes, terminal sessions, filesystem reads, and git operations run on the server you control. The provider CLI you choose may still send prompts and code context to that provider under its own terms.
Linux is the primary target and ships as an x86_64 AppImage. macOS is supported and can be built from source. Ronin uses native backends and does not currently support Windows or WSL.
Not yet. Ronin is currently at version 0.6.0. It is pre-1.0 software and the project explicitly asks users to expect bugs.
Pre-1.0 software
Install and authenticate at least one provider CLI, then launch Ronin from source or pick up a release build. Early software—expect rough edges.
git clone https://github.com/0veek/Ronin.git
cd Ronin
vp i
vp run dev:desktop