AI Skill Hub 强烈推荐：本地AI工作流 是一款优质的Agent工作流。AI 综合评分 8.0 分，在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案，这是一个值得深入了解的选择。
本地AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
本地AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一：npm 全局安装 npm install -g locally-uncensored # 方式二：npx 直接运行（无需安装） npx locally-uncensored --help # 方式三：项目依赖安装 npm install locally-uncensored # 方式四：从源码运行 git clone https://github.com/PurpleDoubleD/locally-uncensored cd locally-uncensored npm install npm start
# 命令行使用
locally-uncensored --help
# 基本用法
locally-uncensored [options] <input>
# Node.js 代码中使用
const locally_uncensored = require('locally-uncensored');
const result = await locally_uncensored.run(options);
console.log(result);
# locally-uncensored 配置说明 # 查看配置选项 locally-uncensored --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export LOCALLY_UNCENSORED_CONFIG="/path/to/config.yml"
<img src="logos/LU-monogram-bw.png" alt="Locally Uncensored" width="80">
%LOCALAPPDATA%\Programs\ComfyUI binary folder with "Invalid path — main.py not found". v2.4.9 walks a probe list when given a folder with ComfyUI.exe until it finds the actual Working Directory with main.py.beforeunload IndexedDB backup → %APPDATA%\Locally Uncensored\rag_chunks_backup.json restores chunks on cold start and on warm starts where IndexedDB is empty.ollama serve no longer lingers as a ~200 MB orphan after a tray-menu Quit. User-managed Ollama running pre-launch is still left alone.getLatestSpeed groups runs into sessions via a 10 s timestamp gap; leaderboard keeps the cross-model average.normalizeFamily rewritten as a greedy strip + suffix/quant peel + family-dash collapse /g, plus word-boundary contains-check.nomic-embed-text for Document Chat / RAG (GH #45 — leonsk29). Auto-detects existing embedding models or offers a one-click 274 MB pull.</details>
<details> <summary>v2.4.8 — superseded</summary>
Hotfix: 8 fixes on top of v2.4.6. All user-reported. v2.4.7 was tagged but not separately released; its six fixes ship together with v2.4.8.
hf.co/<repo>:<quant> references), so whatever Ollama / LM Studio actually have on disk is what the Discover grid shows.canPull:false text models now get a clickable HuggingFace link (Bug T — leonsk29 GH #44). Qwen 3.6 27B Samantha and GLM 5.1 754B MoE both have HF pages but no GGUF on day-one, so they show up as Available rather than downloadable. Before this they had no UI to open the HF page from inside LU. v2.4.8 adds the external-link button next to the Available badge.eval_count / eval_duration from the final stream chunk, with a wall-clock fallback for OpenAI-compat providers when streaming gets buffered. End result: benchmark matches CLI / chat baselines on every provider.git --version before clone (Bug N — juliandiggins-stack GH #40). If a WSL / Linux-mounted git is first on PATH, the previous code let the clone start and die mid-flight with cryptic stderr. New tri-state probe (Native / NonNative / Missing) either proceeds silently, surfaces a clear "install Git for Windows" hint when missing, or logs a soft warning when a non-native git might still work./v1 (Bug O — 0yagizz Discord). Users pointing the Anthropic provider at a proxy (claude-relay-server, LiteLLM, opencode-zen) whose docs end the baseUrl with /v1 got a silent 404 on …/v1/v1/messages. v2.4.8 collapses the duplicate.start_lmstudio_server Tauri command and re-populates the model list without restarting LU.images / gifs / videos from the history payload, missing every community workflow that uses a non-canonical save node (audio, custom metadata, CivitAI flows). v2.4.8 generic extractor accepts any keyed array of file-shaped objects.⚠️ Just want to use the app? Grab the installer from Releases (the.exeor.msiin the Download section above). That gives you the full Tauri desktop app with auto-update. The commands below start LU in browser dev-mode — fewer features, Vite proxy noise, meant for contributing to the codebase.
```bash git clone https://github.com/PurpleDoubleD/locally-uncensored.git cd locally-uncensored setup.bat # Windows — installs Node, Git, Ollama, then npm run dev
```
Launches at http://localhost:5173 in your default browser.
git clone https://github.com/PurpleDoubleD/locally-uncensored.git
cd locally-uncensored
npm install
npm run dev # Development
npm run tauri build # Production binaryNew to Locally Uncensored? Read the Getting Started Guide with screenshots for every step.
| Chat with Personas | Image / Video Generation |
|---|---|
|  |  |
| **Model Manager** | **Create View with Parameters** |
|  |  |
---
A small, dismissible badge to be notified if a hosted version ever arrives — it only sends an email address you choose to type in. Everything else stays on your device.
高质量的开源AI工作流项目，支持多种功能
该工具使用 NOASSERTION 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
总体来看，本地AI工作流 是一款质量优秀的Agent工作流，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。
| 原始名称 | locally-uncensored |
| Topics | aichatimage-genvideo-gentypescript |
| GitHub | https://github.com/PurpleDoubleD/locally-uncensored |
| License | NOASSERTION |
| 语言 | TypeScript |
收录时间：2026-06-07 · 更新时间：2026-06-07 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端