Compare
Up to three tools. The table shows the data as-is, without picking a “best”.
| Field | goose | Miller | dsh-chrome |
|---|---|---|---|
| Platforms | Universal, MCP | Universal, MCP, Claude Code, Codex, Cursor | DeepSeek Harness |
| Local support | Yes | Yes | Yes |
| Paid API | No | No | No |
| License | Apache-2.0 | BSD-2-Clause | MIT |
| Stars | 55588 | 10049 | 9 |
| Last activity | October 23, 2026 | October 21, 2026 | — |
| Install complexity | MEDIUM | EASY | متوسط / Moderate |
| Category | Code Review, Multi-Agent, Workflow | Workflow, Data | Browser Automation, Security |
| Best use | Best for an individual developer or small team that wants an AI agent to complete an inspectable task in a working copy: understand files, make a bounded change, and run a test. Start with manual approval and scope the folder and tools. Do not give it broad access to production or sensitive data. | Ideal for developers, data analysts, and operators who need to clean a CSV export, inspect JSON Lines, or summarize a large file from the terminal without starting a Python project. Use it for quick, repeatable file processing; concurrent transactions and advanced visual analysis still call for a database or complementary analytics tool. | Best for a developer debugging a local or test web UI who wants a DSH agent to see the page and network evidence in the same session. It reduces manual copying and supports interactive inspection after an explicit request. Avoid it for sensitive production accounts or if broad browser permissions are unacceptable. |