Compare
Up to three tools. The table shows the data as-is, without picking a “best”.
| Field | dsh-task-board | Backlog.md | MarkItDown |
|---|---|---|---|
| Platforms | DeepSeek Harness | Universal, Codex, Claude Code, Cursor | Universal |
| Local support | Yes | Yes | Yes |
| Paid API | No | No | No |
| License | Apache-2.0 | MIT | MIT |
| Stars | 9384 | 7130 | 191797 |
| Last activity | — | — | — |
| Install complexity | Intermediate | Easy — npm, Bun, Homebrew, or Nix | سهل / Easy |
| Category | Multi-Agent, Workflow | Multi-Agent, Git, Workflow | Workflow, Research |
| Best use | 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. | Best for an individual developer or small team using coding agents and wanting to review the specification and plan before code. It keeps tasks, acceptance criteria, and decisions inside the project and exposes them through CLI, a local browser, or MCP. It is not a replacement for a centralized enterprise SaaS board with organization-wide permissions and reporting. | 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. |