CheshireJCat/blender
110Last commit Aug 14, 2026
blender DSH plugin
dsh-blender registers one orchestrator, 29 domain skills, 26 analysis helpers, and 13 workspace tools. It launches Blender as a background process to perform scene inspection, import/export, rendering, validation, and Python scripting without any Blender add-on or control port.
How to install the blender DSH plugin
dsh plugin --profile web add dsh-blenderCopying does not run this command. Review the repository and version before installing the blender DSH plugin.
blender DSH plugin data source
blender DSH plugin snapshot date: Aug 16, 2026
discovered
What the blender DSH plugin can do
- Check Blender status, environment, skills, and workspace.
- Inspect scenes and objects for geometry, materials, UVs, constraints, shape keys, and animation.
- Import portable assets (GLB/glTF, FBX, OBJ, STL, USD, PLY) into versioned .blend files.
- Execute reviewed bpy/bmesh Python scripts and save versioned .blend files.
- Generate blockout, look-dev, and animation previews, renders, and frame sequences.
- Export to multiple formats with target-aware validation and re-import checks.
- Run 26 deterministic helpers for reference, wireframe, contour, multiview, UV, texture, look, repair, and animation QA.
Where the blender DSH plugin fits
- Automate 3D modeling workflows within DeepSeek Harness sessions.
- Validate exported assets against target platform requirements.
- Generate preview renders and animation frames for quality assurance.
- Run custom Blender scripts in a controlled, versioned environment.
- Analyze scene geometry, materials, and animation data programmatically.
- Integrate Blender capabilities into larger AI-driven production pipelines.
Who the blender DSH plugin is for
- 3D artists and technical artists who use DeepSeek Harness for AI-assisted workflows.
- Developers building automated 3D content pipelines that include Blender.
- DeepSeek Harness users needing to extend the platform with 3D modeling and rendering skills.
blender DSH plugin limitations
- Requires Blender 4.3+ installed and accessible via PATH or absolute path.
- Requires Node.js 20+ and DeepSeek Harness 0.1.0-rc.6.
- Optional Python 3.10+ is needed for analysis helpers (OpenCV, NumPy, Pillow, SciPy).
- Blender is launched as a background process per operation, which may be slower than persistent add-on integration.
- Setup command installs a private Python virtual environment with additional dependencies.
blender DSH plugin: from the repository README
Quoted from the CheshireJCat/blender README, the upstream source of the blender DSH plugin. Copyright remains with the original authors.
An installable [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) plugin that gives dsh a complete Blender-backed 3D production workflow. It registers one orchestrator plus 29 directly loadable domain skills, all 26 upstream analysis/validation helpers, and 13 workspace-scoped Blender tools. ## Tools - `blender_status` checks Blender, analysis Python, skills, helpers, and the active workspace. - `blender_scene_info` and `blender_object_info` inspect scenes and object-level geometry, materials, UVs, constraints, shape keys, and animation. - `blender_import` converts supported portable assets into versioned `.blend` sources. - `blender_python` runs a small reviewed `bpy`/`bmesh` chunk and saves a versioned `.blend`. - `blender_preview`, `blender_render`, and `blender_render_frames` create blockout, look-dev, and animation evidence for `read_image` QA. - `blender_export` exports GLB/glTF, FBX, OBJ, STL, USD, or PLY. - `blender_validate_scene` and `blender_validate_export` perform target-aware audits and clean-process re-import checks. - `blender_helper_catalog` and `blender_helper_run` expose all 26 deterministic reference, wireframe, contour, multiview, UV, texture
Read the full READMERepository license: MIT
blender DSH plugin questions
How do I install dsh-blender?
Run the installation command: `npx @deepseek-ai/dsh plugin --profile web add dsh-blender`. Then run the setup command: `npx @deepseek-ai/dsh plugin --profile web exec dsh-blender-setup`. This creates a private Python virtual environment with required dependencies. Optionally, you can install a pinned GitHub release: `npx @deepseek-ai/dsh plugin --profile web add github:CheshireJCat/blender#v0.2.1`.
What are the system requirements for dsh-blender?
You need DeepSeek Harness version 0.1.0-rc.6, Node.js 20+, and Blender 4.3+ available on your system's PATH or configured via an absolute path. Python 3.10+ is required only if you want to use the optional reference-analysis helpers. The setup script installs OpenCV, NumPy, Pillow, and SciPy into a private virtual environment.
Can I use dsh-blender without a Blender add-on or control port?
Yes. The plugin does not require any Blender add-on or control port. Each operation launches a local Blender background process, executes the task, and then exits. This makes it easy to integrate with DeepSeek Harness without modifying your Blender installation.
What file formats can dsh-blender import and export?
It can import portable assets (GLB/glTF, FBX, OBJ, STL, USD, PLY) and convert them into versioned .blend files. For export, it supports GLB/glTF, FBX, OBJ, STL, USD, and PLY, with target-aware validation and clean-process re-import checks.
How do I use dsh-blender to create a 3D model?
Open the DeepSeek Harness web interface at http://127.0.0.1:3080, create a session whose workspace is your modeling directory, and ask dsh to use the skill `create-3d-model`. The plugin will leverage Blender to generate the model based on your instructions.