dsh-dglab
Run the following command in DeepSeek Harness:
dsh plugin install lindog114514/dsh-dglab
Paste the following prompt into your AI chat to install this plugin:
Run `dsh plugin install lindog114514/dsh-dglab` in your terminal to install this plugin from the repository at https://github.com/lindog114514/dsh-dglab, then restart dsh web to get started.
About this plugin
Traditional DG-LAB stimulator workflows (Coyote, Opossum, Civet) require manual APP interaction for every parameter change, with no bridge to AI-assisted control. dsh-dglab plugs device control directly into DeepSeek Harness so that natural-language commands drive the hardware safely, eliminating repeated trips to the phone.
The plugin exposes ten dglab_* tools spanning connection lifecycle, status queries, absolute/relative/temporary intensity, waveform playback, cleanup, and disconnect. A locally generated QR-code panel lets the DG-LAB 4 APP pair in one scan. Every stimulation command triggers a three-choice confirmation dialog (run once / allow permanently / deny) with per-session memory. A single shared connection persists across conversations, and device state is silently refreshed on every turn so the AI always reads fresh values.
Ideal for developers and hobbyists who already own a DG-LAB device and want to orchestrate intensity settings and waveforms through DeepSeek Harness conversation.
Use Cases
- Control DG-LAB intensity and waveforms via natural-language AI commands
- Share a single device connection across multiple Harness sessions
- Pair phone via QR scan in the web GUI then let AI take over
Best For
- Developers who own DG-LAB Coyote, Opossum, or Civet devices
- Hobbyists who want to orchestrate hardware workflows in DeepSeek Harness
- E-stim enthusiasts who need AI safety-confirmation mechanisms
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.