Compare
Up to three tools. The table shows the data as-is, without picking a “best”.
| Field | MarkItDown | Hurl | dsh-task-board |
|---|---|---|---|
| Platforms | Universal | Universal | DeepSeek Harness |
| Local support | Yes | Yes | Yes |
| Paid API | No | No | No |
| License | MIT | Apache-2.0 | Apache-2.0 |
| Stars | 191797 | 19271 | 9384 |
| Last activity | — | October 17, 2026 | — |
| Install complexity | سهل / Easy | Easy; API and CLI knowledge required | Intermediate |
| Category | Workflow, Research | Testing, DevOps | Multi-Agent, Workflow |
| Best use | Best for a developer or analyst extracting text from several document formats before search or supplying selected passages to an AI agent. It provides a repeatable CLI command and Python library, while requiring review against the original. It is not intended for layout-perfect document publishing. | Best for a developer or small team that wants repeatable API checks with explicit conditions stored beside the code. It links request data and identifies failing assertions without repeating manual inspection. It does not replace browser tests or test-environment setup; curl may be enough for a one-off request. | Best for a developer or small team using DSH for recurring or connected work and wanting task state and execution evidence in one record. It pins the project, agent preset, and permission, then runs manually or through Host cron with a human gate for elevated access. It is not a fit for a frequently sleeping machine or unreviewed sensitive automation. |