# Unstoppable (slim)

> Unstoppable, from Unstoppable Domains, is a desktop agent IDE for macOS and Windows that runs Claude Code, Codex, Cursor and other coding agents side by side in separate Git worktrees, with Remote Control from iOS, Android and the web.

- Full: https://www.anchorterminal.com/tools/unstoppable.md (~8,750 tokens) · this version ~1,780 tokens · JSON https://www.anchorterminal.com/tools/unstoppable.json · canonical https://www.anchorterminal.com/tools/unstoppable
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-28 · pricing https://www.anchorterminal.com/tools/unstoppable#pricing · reviews https://www.anchorterminal.com/tools/unstoppable#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**F · 34.9/100 · rank #1133 of 1218 · #42 in Agent harnesses · not agent-ready · confidence medium**


Assessment: Unstoppable runs several coding agents side by side in separate worktrees on the owner's Claude, ChatGPT or Cursor plans, with dated help articles and a public changelog. It has no API, MCP server or documented command an outside agent can call, every chat starts in Full access, and its pages disagree on which parts need a paid plan.

## Facts

- Kind: Agent harness · vendor: Unstoppable Domains, Inc. · category: Agent harnesses · legal entity: Unstoppable Domains, Inc. · provenance 76/100
- Auth: None · pricing: Freemium · x402: no · licence: Proprietary, under Unstoppable Domains, Inc.'s Terms of Service. No source published
- Probe metrics: not measured yet (probes haven't run)
- Surface listed: The Unstoppable desktop app (called Unstoppable Code in the app and help) version 1.15.0 for macOS and Windows, with its iOS and Android Remote Control apps and web app, read from the site, help centre, changelog and store listings on 27 October 2026. Nothing was installed, signed in to or bought
- Interfaces: Desktop app, web app and mobile apps for people. No API, MCP server, SDK or documented CLI for an outside agent. The app is an MCP client and has its own agent tools for its chats (start, message and watch chats, schedule turns)
- Agents run: Claude Code, Codex and Cursor on the owner's sign-ins, with Copilot and OpenCode models in 1.15.0, other CLI agents in the integrated terminal, hosted models on AI credits and Ollama models locally
- Approvals: Ask, Accept edits and Full access. New chats start in Full access. Rules by command, file write, MCP tool, network host or tool, with deny winning over allow and safety rules for force-pushes and destructive deletes outside Full access
- Sandbox: Each Code task runs in its own Git worktree on the owner's machine, with no sandbox documented for local agents. Cloud worktrees each get their own sandbox per the 1.12.0 notes
- Network: Model requests go to the chosen provider or to Unstoppable's hosted models on credits. Activity sharing uploads only when set to Just me or Organisation. Updates download automatically by default. Remote Control pairs a phone or browser by a one-time code that expires after 10 minutes
- Telemetry: The privacy policy collects usage telemetry (feature use, session activity, token and spend metrics, diagnostics), synced to the agent cloud depending on activity-sharing settings. No opt-out for the telemetry itself is documented. In-app feedback includes diagnostics by default, with a switch
- Data retention: As long as needed, per the privacy policy. Transcript and observability retention is configurable. Deleted worktrees can be restored for 7 days by default
- Platforms: macOS (Apple Silicon and Intel) and Windows downloads, iOS 15 or later and Android. The changelog also mentions a Linux build for Ubuntu 24.04 LTS that the download page does not list
- Releases in 90 days: Desktop 1.12.0 and 1.13.0 on 20 October, 1.14.0 on 22 October and 1.15.0 on 23 October 2026. iOS 1.1.1 to 1.1.9 from 11 August to 27 October 2026
- Also from Unstoppable Domains: An ICANN-accredited domain registrar with its own API and an MCP server for domains, and web agents for sites, outbound email and social posts at unstoppable.ai. Not graded here

- Scores: Reliability 45, Performance pending, Schema & documentation 30, Agent ergonomics 5, Security & auth 36, Payments & pricing 30, Task success pending, Maintenance & community 58, Transparency & trust 58 · total over the 7 assessed categories
- Why: Reliability, Read as local software, because the product is the desktop app the owner runs, as for the other harnesses. · Schema & documentation, Graded on the interface an outside agent can use, which is none. · Agent ergonomics, These lines measure an interface an agent calls, and Unstoppable has none, so context cost, output controls and retries score nothing. · Security & auth, Harness reading of the framework checklist, as for the other harnesses. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read for a closed product. · Transparency & trust, Closed source under terms of 6 October 2026 that name Unstoppable Domains, Inc.
- Sources: 34, open questions: 10, both in the full twin
- Capabilities: agent.multi-agent, agent.harness, agent.mcp-client, code.git, browser.control
- JSON: https://www.anchorterminal.com/api/v1/tools/unstoppable.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/unstoppable.svg` or a link to https://www.anchorterminal.com/tools/unstoppable from a page on unstoppable.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: Discord https://discord.gg/thU89YfnR; support@unstoppable.ai; https://unstoppable.ai/support; https://unstoppable.ai/support/troubleshooting/contact-support; more in the full twin

## Before you call it

1. Don't plan to drive Unstoppable from another agent. It has no documented API, MCP server or CLI. Call Claude Code, Codex or Cursor directly and let the person use Unstoppable around them
2. Inside Unstoppable, check the approval mode before acting. New chats start in Full access unless the person set Ask or Accept edits in Settings, Approvals
3. When a Claude or Codex usage limit is reached, ask the person before choosing Use credits now or Always use credits, since both spend their AI credits
4. Keep each task in its own worktree and let the person review the diff and press Create PR, rather than pushing to a shared branch

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| goose | BB | 74.3 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/goose.min.md |
| Kilo Code CLI | BB | 73 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/kilo-code-cli.min.md |
| Qwen Code | BB | 72.5 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/qwen-code.min.md |
| OpenHands | BB | 71 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/openhands.min.md |
| OpenCode | B | 68.8 | agent.harness, agent.mcp-client, agent.multi-agent | https://www.anchorterminal.com/tools/opencode.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)