dsh-robotic-harness
An installable DeepSeek Harness bundle for robotics and embodied-intelligence research workflows.
Install
$ dsh plugin --profile rh-demo add ./packages/dsh-bundleRepository Intelligence
AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.
Key Capabilities
- Installs as the @robotic-harness/dsh-bundle DSH bundle.
- Provides roughly 100 rh_* tools and 25 skills across robotics research domains.
- Inspects and validates URDF, MJCF, SDF, CAD inventories, meshes, inertia, and robot topology.
- Runs MuJoCo pick-and-place simulations with deterministic fault injection and replay.
- Analyzes control traces, trajectories, telemetry, anomalies, and candidate failure causes.
- Supports vision, model-routing, data-pipeline, experiment, knowledge-search, and reporting workflows.
- Exports evidence bundles with hash manifests, Markdown reports, timelines, dashboards, and run artifacts.
Useful For
- Inspect robot assets before simulation or experimentation.
- Run a fault-injected MuJoCo pick-and-place experiment and diagnose the results.
- Compare telemetry, trajectories, controller configurations, or experiment runs.
- Prepare datasets, inspect rosbags, create leakage-safe splits, and export data artifacts.
- Generate reproducible experiment evidence and reports for robotics research.
Who It Fits
- Robotics and embodied-AI researchers using DeepSeek Harness.
- Developers building agent-driven simulation and diagnostic workflows.
- Contributors extending DSH robotics tools, skills, scenarios, or adapters.
Documented Limitations
- The project is described as early demo-stage and validated only in a limited local Windows, Anaconda Python 3.10, and DSH 0.1.0-rc.6 environment.
- Installation requires the DSH CLI, pnpm, and a Python 3.10 environment; package metadata requires Node.js >=22.19.
- ROS 2 live tools require the ros2 CLI; without it they return an unavailable-backend diagnostic.
- Real-robot functionality is limited to preflight and state-machine flows until a hardware adapter exists.
- SolidWorks files can be inventoried but are not parsed; FreeCAD deep integration is optional.
- The MuJoCo suction grasp is kinematic, and simulation results are not real-robot evidence.
- Offscreen perception may fall back to ground-truth plus noise simulation when rendering or OpenCV is unavailable.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 6 development, 0 peer, and 0 optional dependencies.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 6 development, 0 peer, and 0 optional dependencies.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 6 development, 0 peer, and 0 optional dependencies.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 6 development, 0 peer, and 0 optional dependencies.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 6 development, 0 peer, and 0 optional dependencies.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 6 development, 0 peer, and 0 optional dependencies.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Traceable source and registry metadata for this entry, kept separate from runtime verification.
- Source repository
- dingkaihu63/dsh-robotic-harness
- Registry source
- Public GitHub repository
- Source snapshot
- 2e719d395d02
- Artifact type
- plugin-bundle
- AI enrichment
- gpt-5.6-terra · 2026-08-14
- Prompt version
- dsh-plugin-enrichment-v3
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 12
- Forks
- 2
- Open issues
- 0
- Last commit
- 2026-08-14
- Last release
- —
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
DeepSeek Harness vision-routing plugin with provider fallback chains and pixel-level image tools.
View plugin →A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Loops (auto-research) and more. #dsh
View plugin →Adds an OpenAI-compatible vision bridge to DeepSeek Harness, forwarding images to a configured vision model and displaying descriptions in a web panel.
View plugin →Persona-driven UX walkthrough plugin for DeepSeek Harness (DSH) - scans React + TypeScript source code for UX issues, pinpoints them, and suggests fixes.
View plugin →