# Tidebreak vs OpenWork

OpenWork and Tidebreak agree on the premise: an open desktop agent, any model, your own keys, your own machine. OpenWork is a desktop GUI built on the OpenCode coding agent, and its strengths run toward automation, connectors, and platform reach. Tidebreak is built around the finished document: sandboxed execution, versioned outputs, and native viewers for the spreadsheets, decks, and PDFs you hand to other people.

## What OpenWork is

OpenWork, from Different AI, a Y Combinator company, launched in January 2026 within days of Anthropic announcing Claude Cowork, and positioned itself as the open alternative. Under the interface it is a desktop GUI for OpenCode, the open-source coding agent, and that heritage gives it a broad base from day one: more than fifty model providers with your own keys, Anthropic-compatible skills and MCP servers that port over as-is, and support for macOS, Windows, and Linux.

It has earned its visibility. It is one of the fastest-growing open agent repositories of 2026, it ships releases multiple times a week, and it has stretched well past the desktop, with a browser version in alpha, chat connectors for WhatsApp, Slack, and Telegram, browser automation, and a team tier for sharing agent setups. If you want one open project that touches everything agents can do right now, this is a reasonable pick.

## Where the two projects part ways

The differences come from heritage. OpenWork inherits the shape of a coding agent that was generalized outward. Tidebreak inherits the shape of a research engine that spent three years producing private equity diligence documents, and was rebuilt in Rust around that job.

**How generated code touches your files.** OpenWork's agent works on your files directly, which is simple and fast. Tidebreak puts generated code inside a sandbox, the native macOS one by default or Docker, E2B, or Daytona, with a network policy per chat. Folder access exists only after you grant it through the system picker, the model never sees an absolute path, and overwriting a file you connected always asks first, in every permission mode.

**What happens to the output.** OpenWork edits files in place. In Tidebreak every file the agent produces enters a versioned catalog: the history is append-only, restoring version two from version five creates version six, and nothing is lost to a bad run. Spreadsheets, Word documents, PowerPoint, and PDFs open in native viewers inside the app, so you can check the actual deliverable, not a preview of it.

**The license.** Both projects are open, with different fine print. OpenWork is open-core: MIT for most of the repository, with an enterprise directory under the Fair Source License. Tidebreak's repository is Apache-2.0 throughout.

**Platforms.** This one goes the other way. OpenWork ships desktop builds for macOS, Windows, and Linux. Tidebreak's packaged build is macOS only, universal for Intel and Apple Silicon, and Windows and Linux currently build from source.

## At a glance

| | Tidebreak | OpenWork |
| --- | --- | --- |
| Made by | Brightwave | Different AI (YC) |
| License | Apache-2.0 throughout | Open-core: MIT plus Fair Source enterprise directory |
| Price | Free; you pay your model provider | Free desktop; team seats $10/user/mo after five |
| Built on | Its own Rust engine | OpenCode |
| Models | Anthropic, OpenAI, Google, xAI, OpenRouter, local via Ollama; ChatGPT plan sign-in | 50+ providers, bring your own keys |
| Code executes | Native macOS sandbox, Docker, E2B, or Daytona | On the host |
| Output history | Versioned, append-only restore | Files edited in place |
| Browser automation | Not yet | Yes |
| Platforms | macOS app; Windows and Linux build from source | macOS, Windows, Linux |

## Choose OpenWork when

- You are on Windows or Linux and want a packaged app today.
- The job is automation: driving a browser, wiring chats and tools together, running the same setup across a team.
- You already use OpenCode, or you want its provider list and its pace of releases.

## Choose Tidebreak when

- The work ends in a document someone else will read, and you want its versions, its viewers, and its history in one place.
- You want generated code to run inside an isolation boundary rather than directly on your machine.
- You would rather start on a ChatGPT plan you already pay for than create API keys first.
- A single permissive license across the whole codebase matters to you.

## Both are young

OpenWork launched in January 2026 and Tidebreak is pre-1.0; both are moving fast enough that parts of this page will age. We will keep it current, and the honest summary should hold: same premise, different instincts about what matters first. Pick by the shape of your work.

---

Canonical: https://www.tidebreak.io/compare/openwork
Updated: 2026-08-17
Site briefing for agents and crawlers: https://www.tidebreak.io/llms.txt