经 AI Skill Hub 精选评估,Next.js ChatGPT 应用模板 获评「推荐使用」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.2 分,适合有一定技术背景的用户使用。
Next.js ChatGPT 应用模板 是一款基于 TypeScript 开发的开源工具,专注于 AI角色扮演、隐私优先、本地部署 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
Next.js ChatGPT 应用模板 是一款基于 TypeScript 开发的开源工具,专注于 AI角色扮演、隐私优先、本地部署 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:npm 全局安装 npm install -g app # 方式二:npx 直接运行(无需安装) npx app --help # 方式三:项目依赖安装 npm install app # 方式四:从源码运行 git clone https://github.com/LettuceAI/app cd app npm install npm start
# 命令行使用
app --help
# 基本用法
app [options] <input>
# Node.js 代码中使用
const app = require('app');
const result = await app.run(options);
console.log(result);
# app 配置说明 # 查看配置选项 app --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 APP_CONFIG="/path/to/config.yml"
# LettuceAI Privacy-first AI roleplay & storytelling app with long-term memory, custom characters, and 20+ providers. Runs on Android, Windows, macOS, and Linux. Overview • Install • Development • Android • iOS • Contributing </div>
LettuceAI is a privacy-focused, free and open-source AI character chat app for immersive roleplay, storytelling, and realistic AI companions with long-term memory that actually lasts.
It is client-side first and supports 20+ AI providers with a bring-your-own-key setup, including OpenAI, Anthropic, Google Gemini, DeepSeek, Mistral, and Groq, plus local models through Ollama and llama.cpp.
LettuceAI is fully free and open source with no paywalls or locked features. Your chats, characters, memories, and API keys stay on your device, so you control your data.
bun install ```
If espeak-ng is not on PATH, the app surfaces this same guidance at runtime. Install it once and restart the app:
winget install eSpeak-NG.eSpeak-NG
Or download an installer from the eSpeak NG releases. Make sure the install directory is on PATH so the espeak-ng command resolves in a fresh shell.
brew install espeak-ng
# Ubuntu / Debian
sudo apt install espeak-ng
# Fedora
sudo dnf install espeak-ng
# Arch / Manjaro
sudo pacman -S espeak-ng
You can also point the app at a custom binary or data dir from the TTS settings panel, which maps to EspeakConfig { bin_path, data_path } and overrides the PATH lookup.
- Install Android Studio and let it install: - Android SDK - Android SDK Platform-Tools - Android command-line tools - Android NDK - Use JDK 17 or newer - Set these env vars in your shell startup files so both interactive shells and non-interactive bash -lc builds see the same Android toolchain:
export ANDROID_SDK_ROOT="$HOME/Android/Sdk"
export ANDROID_HOME="$ANDROID_SDK_ROOT"
export ANDROID_NDK_HOME="$ANDROID_SDK_ROOT/ndk/<your-installed-ndk>"
export NDK_HOME="$ANDROID_NDK_HOME"
export PATH="$ANDROID_SDK_ROOT/platform-tools:$ANDROID_SDK_ROOT/emulator:$ANDROID_SDK_ROOT/cmdline-tools/latest/bin:$PATH"
PowerShell equivalent for the current session:
$env:ANDROID_SDK_ROOT = "$HOME\Android\Sdk"
$env:ANDROID_HOME = $env:ANDROID_SDK_ROOT
$env:ANDROID_NDK_HOME = "$env:ANDROID_SDK_ROOT\ndk\<your-installed-ndk>"
$env:NDK_HOME = $env:ANDROID_NDK_HOME
$env:PATH = "$env:ANDROID_SDK_ROOT\platform-tools;$env:ANDROID_SDK_ROOT\emulator;$env:ANDROID_SDK_ROOT\cmdline-tools\latest\bin;$env:PATH"
- If you use fish, set the same values there too. The most common failure mode is having fish point at one SDK and bash -lc point at another. - Verify your environment before building:
bash -lc 'echo ANDROID_HOME=$ANDROID_HOME; echo ANDROID_SDK_ROOT=$ANDROID_SDK_ROOT; echo ANDROID_NDK_HOME=$ANDROID_NDK_HOME; echo NDK_HOME=$NDK_HOME'
bun run tauri:android:init
```bash
bun run tauri:android:build ```
xcode-select --installsudo gem install cocoapods (or Homebrew)ORT_LIB_LOCATION to the directory containing the ONNX Runtime libraries before buildingexport ORT_LIB_LOCATION=/absolute/path/to/onnxruntime/ios/libs
bun run tauri:ios:init
```bash
bun run tauri:ios:build:ready ```
For llama-gpu-cuda, install the NVIDIA CUDA toolkit and driver on the build machine. For llama-gpu-metal, build on macOS with Xcode command-line tools installed.
Release builds are ad-hoc signed, not notarized (notarization requires a paid Apple Developer account). macOS quarantines apps downloaded from a browser, so the first launch is blocked:
If Finder reports the app is "damaged and cannot be opened", clear the quarantine attribute from a terminal:
xattr -cr /Applications/lettuceai.app
```bash
The repo ships a dedicated workflow that builds and publishes the bundle as a GitHub release asset, and the Android dev/release workflows download and verify it before each build:
- .github/workflows/espeak-android-bundle.yml — workflow_dispatch only. Inputs: tag (release tag, e.g. espeak-android-bundle-v1), espeak_ref, espeak_repo, prerelease. Uploads kokoro-espeak-android-bundle.tar.gz plus a .sha256 sidecar to the chosen release tag. - .github/espeak-android-bundle.env — pin file consumed by both Android workflows:
BUNDLE_TAG=espeak-android-bundle-v1
BUNDLE_ASSET=kokoro-espeak-android-bundle.tar.gz
BUNDLE_SHA256=<sha256 of the published asset>
ESPEAK_NG_REF=master
- .github/workflows/android-build.yml and .github/workflows/android-release-build.yml source the pin file, gh release download the asset into RUNNER_TEMP, verify the sha256, and export KOKORO_ESPEAK_ANDROID_BUNDLE_PATH before tauri android build.
To roll out a new bundle: dispatch Build / eSpeak NG Android Bundle with a fresh tag, copy the printed BUNDLE_TAG / BUNDLE_SHA256 block from the release notes into .github/espeak-android-bundle.env, and commit. From then on Android CI builds pick it up automatically.
隐私导向的AI角色扮演工具,技术栈现代,BYOK设计创新。但项目活跃度一般,生态完善度待提升。
该工具使用 AGPL-3.0 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。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
AI Skill Hub 点评:Next.js ChatGPT 应用模板 的核心功能完整,质量良好。对于AI 技术爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | app |
| 原始描述 | 开源AI工具: Privacy-first AI roleplay & BYOK (Bring Your Own Key) & roleplaying, companion 。⭐59 · TypeScript |
| Topics | AI角色扮演隐私优先本地部署BYOK移动友好 |
| GitHub | https://github.com/LettuceAI/app |
| License | AGPL-3.0 |
| 语言 | TypeScript |
收录时间:2026-05-18 · 更新时间:2026-05-24 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。