What Tidebreak is

Tidebreak is an Apache-2.0, local-first desktop for AI coding agents and finished work. Code mode takes a Git repository from task prompt to reviewed pull request. Work mode turns documents and folders into versioned spreadsheets, presentations, reports, charts, and apps.

Switch surfaces with the Code / Work control at the top of the sidebar.

It runs on your machine. Your conversations, your documents, and the files the agent produces live in a local database and a local folder. Your provider API keys live in your operating system's credential store.

Local-first does not mean the app never talks to the network. Packaged release builds check https://downloads.brightwave.io/tidebreak/ for a signed update 15 seconds after launch and every hour (crates/tidebreak-desktop/src/updater.rs). There is no setting that turns those checks off; development builds do not contact the feed. When a check finds a new version, the app downloads it in the background. To download only when you ask, turn off Download updates automatically in Settings → Updates. The first time you use each feature, the app also downloads:

• the voice helper from downloads.brightwave.io (local transcription)
• Node from nodejs.org (skills and coding engines)
• LibreOffice from download.documentfoundation.org (presentation preview)
• the coding engine you pick from npm

Those installs live under tools/ in the application data directory. You avoid a download by not using that feature. Model, search, sandbox, MCP, and hosted-machine traffic still go to the services you configure.

What you can do with it

• Run coding agents over a repository. Code mode runs Claude Code, Codex CLI, opencode, or Grok CLI in its own git worktree per workspace, with per-turn diffs, a review step, a terminal, and a pull-request flow.
• Work over your own files. In Work mode, attach documents to a chat from the composer, or connect a folder on your machine that the agent can list and read.
• Run code in a sandbox. The agent writes and executes scripts to analyze spreadsheets, render PDFs, build charts, and generate documents. Commands run inside the code-execution backend you choose. Network access is a separate per-chat policy that starts open and can be narrowed to package registries, exact hosts, or fully offline.
• Produce files, not just answers. Anything the agent saves to its output/ directory becomes a versioned output you can preview and export with a native save dialog.
• Build reusable local apps. Ask for a triage view or other small tool once, then reopen it from the Apps library. Its access is pinned to the exact folders and connected-app operations you approve.
• Connect outside tools. Add MCP servers for chat tools, or a REST API from an OpenAPI document for local apps to call through Tidebreak's governed executor.
• Use the model routes you prefer. Anthropic, OpenAI, Google, xAI, Fireworks, Together, OpenRouter, a local Ollama daemon, and any OpenAI-compatible endpoint. You can switch models mid-conversation without losing the thread.
• Decide how much rope to give it. Every chat and every coding session has a permission mode, from read-only planning up to full autonomy.

Who it's for

People who want an agent that can touch real data and produce real artifacts, and who would rather that happen on their own machine than in someone else's cloud. You can sign in with a ChatGPT subscription, provide an API key, or use a local Ollama model.

What it is not

It is not a hosted SaaS you log into for local work, and there is no Tidebreak account to create for the desktop. Hosted machines and a mobile client exist for people who attach through Model Gateway. It is not an IDE: keep your editor for hands-on coding, and use Tidebreak to coordinate agents, isolate their work, review what they changed, and carry the result through CI and pull request delivery. And it is not finished: the product is still pre-1.0.

Start here