Process your emails with AI directly in Thunderbird
Summarize • Translate • Correct • Reply • Chat

Features • Providers • Installation • Configuration • Usage • FAQ

• 💬 Interactive Chat - Continue conversations with AI
• 📝 Direct Insert - Insert responses directly into your email
• 🔄 Regenerate - Get a new response with one click
• ⚙️ Custom Actions - Add your own prompts

Quill supports 3 AI providers - choose based on your needs:

1. Download quill-1.2.0.xpi from Releases
2. In Thunderbird: Menu ☰ → Add-ons and Themes (or Ctrl+Shift+A)
3. Click ⚙️ → Install Add-on From File...
4. Select the .xpi file and click Add

git clone https://github.com/mikecastrodemaria/Quill.git
cd Quill/plugin

Then in Thunderbird: Menu ☰ → Add-ons → ⚙️ → Debug Add-ons → Load Temporary Add-on → select manifest.json

Best for: High-quality responses, complex tasks

1. Create account at console.anthropic.com
2. Go to API Keys → Create Key
3. Copy your key (format: sk-ant-api03-...)
4. In Quill settings:
   • Provider: Anthropic (Claude)
   • Paste your API key
   • Recommended model: Claude Sonnet 4.5

Pricing: ~$3/million input tokens, ~$15/million output tokens

Best for: GPT ecosystem users, fast responses

1. Create account at platform.openai.com
2. Go to API Keys → Create new secret key
3. Copy your key (format: sk-proj-...)
4. In Quill settings:
   • Provider: OpenAI (GPT)
   • Paste your API key
   • Recommended model: GPT-4o

Pricing: ~$2.50/million input tokens, ~$10/million output tokens

Best for: Privacy, offline use, no API costs

# Download from https://ollama.ai or use Homebrew:
brew install ollama

curl -fsSL https://ollama.ai/install.sh | sh

# Recommended for email tasks:
ollama pull llama3

# Other good options:
ollama pull mistral      # Faster, lighter
ollama pull qwen2.5      # Good multilingual
ollama pull mixtral      # More powerful (needs 32GB+ RAM)

Thunderbird extensions require CORS headers. Configure Ollama:

# Quit Ollama app first (Menu bar → Quit)
OLLAMA_ORIGINS="*" ollama serve

# Set environment variable
launchctl setenv OLLAMA_ORIGINS "*"

cat > ~/Library/LaunchAgents/com.ollama.env.plist << 'EOF'
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>Label</key>
    <string>com.ollama.env</string>
    <key>ProgramArguments</key>
    <array>
        <string>sh</string>
        <string>-c</string>
        <string>launchctl setenv OLLAMA_ORIGINS "*"</string>
    </array>
    <key>RunAtLoad</key>
    <true/>
</dict>
</plist>
EOF

launchctl load ~/Library/LaunchAgents/com.ollama.env.plist

# Edit the service file
sudo systemctl edit ollama

# Add these lines:
[Service]
Environment="OLLAMA_ORIGINS=*"

# Restart service
sudo systemctl restart ollama

OLLAMA_ORIGINS="*" ollama serve

[Environment]::SetEnvironmentVariable("OLLAMA_ORIGINS", "*", "User")

# Should return your models list:
curl http://localhost:11434/api/tags

# Test with CORS header:
curl -H "Origin: moz-extension://test" http://localhost:11434/api/tags

1. In Quill settings:
   • Provider: Ollama (Local)
   • URL: http://localhost:11434 (default)
   • Select your downloaded model

1. Open a compose window (New, Reply, or Forward)
2. Select text to process (or leave empty for entire email)
3. Click the Quill icon (toolbar, top right)
4. Choose an action from the dropdown
5. Wait for AI to process
6. Insert result or Regenerate for a new response

1. After getting a response, click "Convert to Chat"
2. Continue the conversation with follow-up questions
3. AI remembers context from your email

1. Go to Quill Settings
2. Scroll to Actions section
3. Click Add an action
4. Enter name and prompt
5. Save

Example custom prompts:

Name: Simplify
Prompt: Rewrite this text using simpler words and shorter sentences.

Name: Extract Tasks
Prompt: Extract all action items and tasks from this email as a numbered list.

Name: Professional Tone
Prompt: Rewrite this maintaining the message but with a more professional business tone.

# Check if Ollama is running:
curl http://localhost:11434/api/tags

# Check CORS headers:
curl -v http://localhost:11434/api/tags 2>&1 | grep -i "access-control"

# Restart Ollama with CORS:
pkill ollama
OLLAMA_ORIGINS="*" ollama serve

Contributions welcome!

1. Fork the repository
2. Create a branch: git checkout -b feature/improvement
3. Commit changes: git commit -m 'Add feature'
4. Push: git push origin feature/improvement
5. Open a Pull Request

GPL-3.0 - See LICENSE

Fork of Aify by Ali Raheem.

• Development: Supersonique Studio SARL
• Original Project: Aify by Ali Raheem
• AI Providers: Anthropic, OpenAI, Ollama

Made with ❤️ by Supersonique Studio SARL

🇫🇷 Version Française • 📚 Wiki • 🐛 Report Bug