Obsidian plugins with #deepseek-ai#

The Yuhanbo Task plugin manages one time and recurring tasks as Markdown files stored in configurable vault folders. It tracks progress, due dates, execution dates and subtasks, and it can archive completed tasks as separate Markdown files. Task creation and review are exposed through commands, and folder shortcuts open the generated task files directly. The plugin also includes a configurable Pomodoro timer with work and break sessions, cycle intervals and optional sound notifications. An optional AI task splitting feature can send the task title, description and a chosen prompt file to DeepSeek so it can propose subtasks before saving.

The DeepSeek Harness Native plugin embeds the local DeepSeek Harness panel in the note sidebar, keeping its agent conversations, code execution and document retrieval within the workspace. It connects only to a DSH service on 127.0.0.1 and can start that service automatically when the panel opens. Notes or selected content can be sent to DSH, while generated results can be written back into the vault. The panel supports new, existing and historical sessions, streams DSH responses with reasoning content and provides controls for switching between DeepSeek V4 Flash and Pro models. Queue and steer execution modes are available from the panel. Its settings cover the service port, startup command, automatic launch, vault workspace path and sending mode, with DSH listening on port 3080 by default.

The Deepseek AI Assistant plugin integrates Deepseek AI directly into notes, enabling users to ask questions and insert responses seamlessly. It supports a problem-driven learning approach by letting you enrich your notes with AI-generated answers. Additionally, the plugin tracks and visualises all questions asked over the past three months, helping users reflect on their curiosity trends and compare past and present interests.