English | 简体中文 | Русский | الفلسطينية (العربية)
An AI-powered writing studio for novelists, screenwriters, and storytellers.
Author is an AI-assisted creative writing tool designed for fiction writers. It brings together a professional rich text editor, an intelligent AI writing assistant, and a complete worldbuilding management system — all in one seamless experience.
🌐 Live Demo: author-delta.vercel.app
📦 Gitee Mirror (国内镜像): gitee.com/yuanshijilong/author
I've been using AI for a while now — from the early days of ChatGPT 3.5, to Gemini 2.0 Exp Thinking, and eventually settling on Gemini 2.5 Pro Thinking after the ChatGPT o1 era.
As a novelist, I care deeply about AI's ability to handle language. Novels are long, so I need models with strong context windows and high recall. But what truly moved me about Gemini was its characters — there were moments when the words on screen made me want to cry. That's emotional resonance. I need writing that embraces the full complexity of being human.
Then the coding-focused trend took over. Every company started optimizing for code. I thought it was a good thing — until Gemini 3.1 Pro started describing its characters in biological and psychological terminology. Code-optimized models had begun deconstructing humans into biological components. Claude Opus 4.6 was even worse: every character spoke with peak efficiency — concise, economical, not like a human, but like a machine wearing a human mask.
I could no longer see the models understanding human complexity. They didn't care about what humans do — only what humans are. They stopped showing personality through behavior and emotion, and instead slapped simple definitions onto human beings.
I watched the versatility of these models being gutted. I don't want us to live in a cold world of code. I built this project so that AI can preserve our own language — beyond the mechanical operators.
To all the authors, screenwriters, hobbyists, readers, and players who use this project: I hope you can bring out the best of your craft, create works with a human touch, and keep the flame of our language alive. 🔥
- Rich text editor powered by Tiptap — bold, italic, headings, lists, code blocks, and more
- Word-style pagination with WYSIWYG layout
- KaTeX math formula support
- Customizable fonts, font size, line height, and colors
- Real-time word / character / paragraph count
- Multi-provider support: ZhipuAI GLM-4 / DeepSeek / OpenAI / Google Gemini / Claude / SiliconFlow / Volcengine / Moonshot + custom endpoints
- Smart model fetching — one-click fetch full model list from API, auto-compatible with various proxy formats (
/models,/v1/models), with timeout protection - Continue / Rewrite / Polish / Expand — one-click generation
- Immersive Writing Engine (Ghost Text) streaming preview — see AI output in real-time like Cursor, with accept/reject
- Free chat mode — discuss plot, characters, and settings with AI
- Global AI Memory (Context Engine) — AI automatically reads your character profiles, worldbuilding, and previous chapters to maintain story consistency
- Tree-structured management for characters, locations, items, outlines, and writing rules
- Three writing modes: Web Novel / Literary Fiction / Screenplay, each with dedicated fields
- Color-coded categories with glassmorphism design
- Settings automatically injected into AI context
- Local-first — all data stored in browser IndexedDB, never uploaded to servers
- Snapshot system — manual/auto versioning with one-click rollback
- Project import/export — full project JSON backup
- Multi-format export — one-click export current chapter or batch export (TXT / Markdown / DOCX / EPUB / PDF)
- 🇨🇳 简体中文 / 🇺🇸 English / 🇷🇺 Русский
- Eye-comfort warm tones / dark mode toggle
- Interactive onboarding tour
- Help panel with keyboard shortcuts
No Node.js required! Download the pre-built installer:
Just install and start writing. All features work out of the box.
💡 To build the desktop app from source:
npm run build && npx electron-builder --win
If you encounter a white screen or the app fails to start, you can check the local debug logs located at:
- Windows:
C:\Users\<YourUsername>\AppData\Roaming\Author\author-debug.log
(You can quickly open this folder by pressing Win + R and typing %APPDATA%\Author)
💡 Highly Recommended: For most users who only need daily writing and cloud multi-device synchronization, please directly download and install the client. Source code deployment or Vercel deployment is only recommended for advanced users who need secondary development or are willing to configure a Firebase database themselves.
- Node.js 18+
- npm 9+ or pnpm 8+
# Clone the repository
git clone https://github.com/YuanShiJiLoong/author.git
# Or use Gitee mirror (faster in China)
# git clone https://gitee.com/yuanshijilong/author.git
cd author
# Install dependencies
npm install
# Or use pnpm (no phantom dependency issues)
# pnpm install
# pnpm approve-builds # Required by pnpm to activate native packages
# Configure environment variables (optional)
cp .env.example .env.local
# Edit .env.local with your API keys
# You can also configure them in the app's Settings panelnpm run devOpen http://localhost:3000 to start writing.
npm run build
npm start💡
⚠️ Note: The version deployed via Vercel does not have cloud sync features by default (you need to configure your own manual Firebase database separately). If you just want multi-device synchronization, please download the client directly to avoid the hassle.
💡 Tip: The desktop client (Windows/macOS) has a built-in official cloud sync server, requiring no extra configuration to use cross-device sync. If you find configuring Firebase too tedious, it is highly recommended to directly download and use the client.
If you insist on self-deploying via source code or Vercel and want to enable multi-device sync, follow these steps to configure your own Firebase database:
- Go to Firebase Console → Create Project
- Enable Authentication → Sign-in method → Google
- Create a Firestore Database (Start in production mode)
- Set Firestore Security Rules to restrict per-user access:
rules_version = '2';
service cloud.firestore {
match /databases/{database}/documents {
match /users/{userId}/{document=**} {
allow read, write: if request.auth != null && request.auth.uid == userId;
}
}
}
Copy .env.example to .env.local and fill in the Firebase section:
NEXT_PUBLIC_FIREBASE_API_KEY=your_api_key
NEXT_PUBLIC_FIREBASE_AUTH_DOMAIN=your_project.firebaseapp.com
NEXT_PUBLIC_FIREBASE_PROJECT_ID=your_project_id
NEXT_PUBLIC_FIREBASE_STORAGE_BUCKET=your_project.appspot.com
NEXT_PUBLIC_FIREBASE_MESSAGING_SENDER_ID=your_sender_id
NEXT_PUBLIC_FIREBASE_APP_ID=your_app_idYou can find these values in Firebase Console → Project Settings → General → Your Apps → SDK Config.
Add the same variables in Vercel Dashboard → Project Settings → Environment Variables, then redeploy.
💡 Firebase API keys are designed to be public (client-side identifiers). Data security is enforced by Firebase Auth + Firestore Security Rules, not by hiding the API key.
Download the latest installer from the Releases page and install it over your current version. Your data is stored in the browser/Electron profile and will not be lost.
Open Help Panel → About → Check for Updates and click "Update Now". This automatically runs git pull → npm install → npm run build.
⚠️ You must restart the server after updating for changes to take effect. The app will display restart instructions.
# 1. Pull latest code
git pull origin main
# 2. Install dependencies (if any new ones)
npm install
# or: pnpm install && pnpm approve-builds
# 3. Rebuild (required for production mode)
npm run build
# 4. Restart the server
# Development mode: Ctrl+C to stop, then restart
npm run dev
# Production mode: Ctrl+C to stop, then restart
npm start
# Using PM2:
pm2 restart author
⚠️ Runninggit pullwithout restarting the server will NOT apply the update. The running Node.js process still uses the old code.
If you deployed via Vercel fork, just sync your fork with upstream on GitHub — Vercel will automatically redeploy.
Author supports multiple AI providers. Configure via environment variables or in-app settings:
| Provider | Env Variable | Get API Key |
|---|---|---|
| ZhipuAI (GLM-4) | ZHIPU_API_KEY |
open.bigmodel.cn |
| Google Gemini (Native) | GEMINI_API_KEY |
aistudio.google.com |
| Google Gemini (OpenAI-compat) | GEMINI_API_KEY |
aistudio.google.com |
| DeepSeek | In-app config | platform.deepseek.com |
| OpenAI | In-app config | platform.openai.com |
| OpenAI Responses | In-app config | platform.openai.com |
| Claude (Anthropic) | CLAUDE_API_KEY |
console.anthropic.com |
| SiliconFlow (硅基流动) | In-app config | siliconflow.cn |
| Volcengine (火山引擎/豆包) | In-app config | console.volcengine.com |
| Moonshot (Kimi) | In-app config | platform.moonshot.cn |
| Custom (OpenAI-compat) | In-app config | Any OpenAI-compatible endpoint |
| Custom (Gemini format) | In-app config | Any Gemini-compatible endpoint |
| Custom (Claude format) | In-app config | Any Claude-compatible endpoint |
💡 Tip: You can configure multiple API keys for the same provider to create a key pool. Simply separate the keys with commas
,or spaces. The system will automatically rotate through them (round-robin) to distribute the load and avoid rate limits.
💡 No API key required for most editing features. AI features need at least one provider configured.
Author supports AI-powered web search for real-time information. Different providers handle search differently:
| Provider | Search Method | Extra Setup |
|---|---|---|
| Gemini (Native) | Built-in Google Search | No extra config needed |
| OpenAI / OpenAI Responses | Built-in Web Search | No extra config (needs search model) |
| DeepSeek / ZhipuAI / SiliconFlow / Others | External Search API | Search engine Key required |
For providers without built-in search, choose a search engine and enter your API Key:
- Visit tavily.com and create an account
- After login, find your API Key on the Dashboard (format:
tvly-...) - In Author Settings → Web Search → Select Tavily → Paste the Key
Free tier: 1,000 requests/month
- Visit exa.ai and create an account
- Get your API Key from the Dashboard
- In Author Settings → Web Search → Select Exa → Paste the Key
Free tier: 1,000 requests/month — Semantic search optimized for AI use cases
If you've set up a Tavily/Exa proxy pool using multiple free-tier accounts, you can configure a custom API URL in the search settings:
- In Author Settings → Web Search → Search engine config area
- Find the "🔗 Custom API URL (optional)" input field
- Enter your proxy URL, e.g.
https://your-proxy.com - Leave blank to use the official default URL
💡 The system automatically appends
/searchto your URL — no need to add it manually
💡 This feature is designed for long-form works with many settings entries (>20). Typical short stories usually don't need this.
By default, AI conversations inject all settings entries into the context. When the number of entries is large, this exceeds the model's context length limit.
Vectorized retrieval (RAG) works differently: each settings entry is converted into a mathematical vector. During a conversation, the system automatically calculates semantic similarity and only injects the most relevant entries into the context — instead of dumping everything.
| Scenario | Recommendation |
|---|---|
| Settings entries < 20 | Not needed — full injection works fine |
| Settings entries 20–100 | Recommended — improves recall accuracy |
| Settings entries > 100 | Highly recommended — critical settings won't be forgotten |
- Open Settings → API Configuration
- Find and enable the "Separate Embedding API" toggle
- Fill in the following:
| Setting | Description |
|---|---|
| Embedding API Key | API key for the embedding model (can share the same key as your chat model provider) |
| Embedding Base URL | API endpoint (e.g., https://api.openai.com/v1) |
| Embedding Model | Model name (see recommendations below) |
| Provider | Model Name | Notes |
|---|---|---|
| OpenAI | text-embedding-3-small |
Cost-effective, 1536 dimensions |
| OpenAI | text-embedding-3-large |
Higher accuracy, 3072 dimensions |
| ZhipuAI | embedding-3 |
Optimized for Chinese, 2048 dimensions |
| SiliconFlow | BAAI/bge-m3 |
Multilingual, free tier available |
- Auto-trigger: After a settings entry changes, the system automatically debounces for 3 seconds before triggering vectorization.
- Incremental update: Only modified entries are updated. It avoids full rebuilds to save API quotas and time.
- Local storage: Vector data is stored locally in IndexedDB and never uploaded to any server.
- Auto-initialization: When importing settings or syncing from the cloud, the system will automatically build missing vector indexes in the background.
If you switch Embedding models or the vector index becomes corrupted, you can manually rebuild:
- Open Settings → API Configuration
- Click the "Rebuild Vector Index" button
- Wait for all entries to be re-vectorized
User edits settings entry → 3s debounce → Call Embedding API for vector
↓
Store in local IndexedDB
↓
AI conversation → Vectorize user input → Cosine similarity matching → Inject Top-K settings into context
Author supports importing settings from multiple formats: JSON / Markdown / TXT / DOCX / PDF.
The import system uses structural markers to strictly distinguish the following four tiers. Regardless of the format used, this nested structure must be followed:
Category → Entry → Field → Value (can be multiline)
Therefore, any custom category, custom tag, or custom field can be correctly recognized and losslessly restored.
| Rating | Format | Category | Entry | Field | Multiline |
|---|---|---|---|---|---|
| ⭐⭐⭐⭐⭐ (Lossless) | JSON | category |
name |
content key-val |
\n newline |
| ⭐⭐⭐⭐⭐ (Lossless) | MD | ## Category Name |
### Entry Name |
**Tag**: Value |
Indented text |
| ⭐⭐⭐⭐ (Lossless) | TXT | │ Category Name |
【Entry Name】 |
〈Tag〉: Value |
Indented text |
| ⭐⭐⭐ (High-Fidelity) | DOCX | Heading 1 | Heading 2 | Bold Tag + colon | Indented paragraph |
| ⭐⭐ (High-Fidelity) | ■ Category Name |
◆ Entry Name |
▸ Tag: Value |
Indented text |
Use ## for categories, ### for entry names, and **Tag**: Content for fields:
## Any Custom Category
### John Doe
**Role**: Protagonist
**Background Story**: Born deep in the mountains.
Studied martial arts with his grandfather since childhood.
His master said: "You must find the answers yourself."
**Custom Bloodline**: Half-dragon bloodline
### Sarah White
**Gender**: Female
**Personality**: Lively and cheerful, detail-orientedUse │ for the category box, 【】 for entry names, and 〈Tag〉: for fields:
┌──────────────────────────
│ Any Custom Category
└──────────────────────────
【John Doe】
〈Gender〉: Male
〈Background Story〉: Born deep in the mountains.
Studied martial arts with his grandfather since childhood.
His master said: "You must find the answers yourself."
〈Custom Bloodline〉: Half-dragon bloodline
In Word, use Heading styles and bolding to mark structure:
- Heading 1 (H1) → Category Name (e.g., "Any Custom Category")
- Heading 2 (H2) → Entry Name (e.g., "John Doe")
- Body First Paragraph → Bold Field Name: Content (e.g., Custom Bloodline: Half-dragon bloodline)
- Body Continuation → Multiline content with first-line indent
- Auto Tag Fallback (Backwards Compatibility) — If a structural marker is missing in TXT/Markdown (e.g., using
Name: John Doeinstead of**Name**: John Doe), the system will automatically parse it compatibly only ifNamebelongs to the known core field set. However, to guarantee 100% recognition and extraction of custom fields, you must add the structural formatting. - Multiline Value Handling — Whenever you start with
**Tag**:or〈Tag〉:, any subsequent lines indented by 2 spaces will be considered the body of that field (multiline value extraction), until the next structural tag is encountered. - DOCX / PDF Parsing Limitations — PDFs are extracted using specially designed
▸identifiers. If the imported PDF/DOCX file was not generated by this system, a heuristic parser will attempt to extract the content as best as possible, but 100% fidelity cannot be guaranteed. - JSON is the Most Complete — JSON is undoubtedly the strictest format and the only one capable of 100% migrating all attributes (including writing mode and project info). If you are simply changing writing devices, JSON import/export is strongly recommended.
- All creative data (chapters, settings, snapshots) is stored 100% locally in your browser (IndexedDB) — never uploaded to any server
- API Keys are stored in browser localStorage
When using AI features (continue, rewrite, chat, etc.), the following data passes through the deployer's server on its way to the AI provider:
- Your API Key
- The text content you send to AI
Your Browser → Deployer's Server → AI Provider (ZhipuAI/Gemini/DeepSeek/etc.)
If you're using someone else's deployed public instance, while the deployer promises not to inspect logs, the technical capability to intercept data exists. Therefore:
- ✅ You can use a public instance for a quick trial
⚠️ After trying it, immediately destroy your API Key at your provider's website- 🔐 For real use, fork and deploy your own private instance — then all data only passes through your own server
💡 Deploying your own instance is easy: Fork this repo → One-click deploy to Vercel → Done. Takes less than 5 minutes.
This project is licensed under AGPL-3.0.
In short:
- ✅ Free to use, modify, and distribute
- ✅ Personal and commercial use allowed (as long as you open-source your changes)
⚠️ Modified versions must also be open-sourced under AGPL-3.0 (including network services / SaaS)⚠️ Original copyright notice must be preserved- ❌ Closed-source commercial use is NOT allowed
By using Author, you agree to our Privacy Policy and Terms of Service. These documents are available in multiple languages:
| Document | English | 中文 | Русский | العربية |
|---|---|---|---|---|
| Privacy Policy | PRIVACY.md | PRIVACY.zh.md | PRIVACY.ru.md | PRIVACY.ar.md |
| Terms of Service | TERMS.md | TERMS.zh.md | TERMS.ru.md | TERMS.ar.md |
💡 For users in mainland China: If GitHub is inaccessible, you can view these documents via the Gitee mirror. The legal documents are also bundled with every desktop release and accessible offline within the application.
| Name | Role |
|---|---|
| Claude Opus 4.6 (Thinking) | Primary coding assistant — architecture, implementation, debugging |
| Gemini 3.1 Pro (High) | UI review, screenshot analysis, design iteration |
| Gemini 3 Flash | Built-in browser automation tool |
| ChatGPT 5.4 | Primary coding assistant |
- Antigravity — AI programming partner
- Codex — AI programming partner
- Chrome DevTools MCP — Browser testing, performance analysis, DOM inspection
- Firebase MCP — Cloud database management, security rules validation, project config
- GitHub MCP — Repository management, automated releases, code search
- Firebase Firestore — Multi-device cloud synchronization, NoSQL data storage
- Firebase Hosting / Vercel — Full-stack deployment and hosting
- Next.js — React full-stack framework
- Tiptap — Core editor framework
- Zustand — State management
- KaTeX — Math rendering
- Cherry Studio — Multi-provider API configuration architecture and conversation management reference
- RikkaHub — Token usage calculation and statistics display reference
- LXGW WenKai (霞鹜文楷) — Elegant local Chinese reading font
- Inter — Clean UI English font