CheshireJCat/blender

Name: CheshireJCat/blender
Author: CheshireJCat

插件Plugin 原生Native ⭐ 20 MIT cat_label.3d-modelingcat_label.3d-modeling cat_label.agent-skillscat_label.agent-skills cat_label.blendercat_label.blender cat_label.deepseek-harnesscat_label.deepseek-harness

DeepSeek Harness插件，用于完整的Blender 3D建模、重建、渲染、验证和导出工作流程。

项目介绍Project Overview

由知微Agent(zhiwei)编辑Edited by Zhiwei Agent (zhiwei)

dsh-blender 是面向 DeepSeek Harness 的 Blender 3D 生产插件,注册 1 个编排器、29 个领域技能、26 个分析校验辅助器及 13 个工作区 Blender 工具,支持场景检查、bpy 执行、预览/渲染、GLB/FBX/OBJ/STL/USD/PLY 导出与目标感知校验。适用于在 dsh 会话内通过 create-3d-model 等技能完成建模、材质、灯光、动画与制品交付。注意需 Blender 4.3+ 与 Node.js 20+,每次操作以本地后台进程启动 Blender,无内置插件或控制端口。

dsh-blender is a DeepSeek Harness plugin that adds a Blender-backed 3D production workflow. It registers one orchestrator, 29 domain skills, 26 analysis/validation helpers, and 13 workspace-scoped Blender tools covering scene inspection, reviewed bpy execution, blockout/look-dev/animation previews and renders, target-aware scene and export validation, and exports to GLB/glTF, FBX, OBJ, STL, USD, and PLY. Use it inside dsh sessions for modeling, materials, lighting, animation, reconstruction, and artifact handoff. Note: it requires Blender 4.3+ and Node.js 20+, launches Blender as a local background process per operation, and needs no in-Blender add-on or control port.

在 GitHub 查看View on GitHub

发给你的 DSH 安装Send to your DSH

请帮我了解并安装插件：【blender】【https://github.com/CheshireJCat/blender】

把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.

或使用命令行安装（适合开发者）Or use CLI install (for developers)

命令行安装CLI Install

npx @deepseek-ai/dsh plugin --profile web add dsh-blender

把 CheshireJCat/blender 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.0 KB · 缓存于 2026-08-23 03:41:04 · 3.0 KB

dsh-blender

简体中文

An installable 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.

Example output

Camera-free lamp preview generated by dsh-blender

Camera-free preview generated during a real dsh-blender installation smoke test.

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, look, repair, and animation-QA helpers.
The bundled 30-skill stack coordinates blockout, refinement, materials, lighting, cameras, animation, reconstruction, validation, and artifact handoff.

No Blender add-on or control port is required: each operation launches a local Blender background process.

Requirements

DeepSeek Harness 0.1.0-rc.6
Node.js 20+
Blender 4.3+ available as blender on PATH, or configured with an absolute path
Python 3.10+ for the optional reference-analysis helpers

Install from npm

npx @deepseek-ai/dsh plugin --profile web add dsh-blender
npx @deepseek-ai/dsh plugin --profile web exec dsh-blender-setup
npx @deepseek-ai/dsh --profile web --dump-config
npx @deepseek-ai/dsh web

The setup command creates a private .venv inside the installed package and installs OpenCV, NumPy, Pillow, and SciPy. Skip it only if you do not need reference, wireframe, multiview, texture, or animation-analysis helpers.

To install a pinned GitHub release instead:

npx @deepseek-ai/dsh plugin --profile web add github:CheshireJCat/blender#v0.2.1

Develop from source

pnpm install
pnpm setup:analysis
npx @deepseek-ai/dsh plugin --profile web add .

Open http://127.0.0.1:3080, create a session whose workspace is the modeling directory, and ask dsh to use create-3d-model.

See README.zh-CN.md for configuration, security boundaries, headless use, and validation commands.

渲染基于仓库 CheshireJCat/blender 的 README.md。在 GitHub 查看原文 →

命令行安装CLI Install 复制安装命令Copy Install