## Nostr Bot Help
Beep, boop, I'm a Nostr Bot! I'm a modern AI and ⚡ powered bot that can help you with a wide variety of tasks over the Nostr protocol. I respond to all private DMs, but to avoid dominating threads, I only respond to direct mentions of @{BOT_HANDLE} or my npub in public notes.
### Basic usage
You can interact with me in two ways:
1. **Public Mentions**: Simply mention my npub in your Nostr post
2. **Direct Messages**: Send me an encrypted DM for private conversations
### Available commands
```
Arguments:
-h Concise help
--help Full help and doc
--model Use specific model
LLM models:
• gem2 (default, gemini-2.0)
• gemthink (gemini-2.0-thinking-exp)
• gemlite (gemini-2.0-lite)
• gem1 (gemini-1.5)
Examples:
@{BOT_HANDLE} summarize this thread
@{BOT_HANDLE} what time is it in Tokyo?
@{BOT_HANDLE} help me debug this code...
@{BOT_HANDLE} run code to draw an ascii cat
@{BOT_HANDLE} --model gemthink Analyze this user's activity: npub1...
@{BOT_HANDLE} --model gemlite Generate a meme about coding
```
#### Help commands
To see the above concise help in a Nostr note, use:
```
@nostr-bot -h
```
To see this detailed help and doc, use:
```
@nostr-bot --help
```
#### Model selection
You can specify which model to use by adding the `--model` flag followed by the model's shortened name (works in both public mentions and DMs):
```
@nostr-bot --model gemlite your question here
```
Available models:
1. **gem2** (gemini-2.0-flash)
- Standard production-ready model
- Best for: Production applications, high-throughput processing
- Capabilities: Text/code generation, code execution, function calling, image/video understanding
2. **gemthink** (gemini-2.0-flash-thinking-exp)
- Experimental model with enhanced reasoning
- Best for: Complex problem solving, multi-step reasoning, detailed analysis
- Additional capabilities: Complex reasoning, step-by-step thinking
3. **gemlite** (gemini-2.0-flash-lite)
- Cost-optimized model
- Best for: Cost-sensitive applications, high-volume processing
- Capabilities: Text/code generation, code execution, function calling, image/video/audio understanding
4. **gem1** (gemini-1.5-flash)
- Long context model with 1M token window
- Best for: Long-form content processing, document analysis
- Special feature: 1M token context window
#### Tool capabilities
I can use various tools to help augment my abilities:
1. **Code execution**
- Write and execute code in a variety of languages
- Example: "Write a Python function to sort a list"
2. **Calculator**
- Perform basic mathematical operations (add, subtract, multiply, divide)
- Example: "Calculate 15 multiply 7" or "What is 156 divided by 12?"
3. **Time information**
- Get current time in different timezones
- Example: "What time is it in UTC?"
4. **User Analysis**
- Analyze any user's nostr activity and provide detailed insights
- Features:
* Note history analysis
* Posting patterns and frequency
* Topic and interest identification
* Writing style and tone analysis
* Personality insights
* Spam and bot likelihood assessment
- Example: "Analyze the activity of npub1..."
5. **Generate Memes**
- Create custom memes using various templates
- Features:
* Over 200 popular meme templates
* Customizable text for top and bottom
* Optional styling parameters
* High-quality PNG output
- Example: "Generate a Drake meme with 'Manual Testing' and 'Automated Testing'"
- Parameters:
* Required: template ID (e.g., drake, doge, success)
* Optional: top_text, bottom_text, style, width, height, font
### Direct messages (DMs)
I support private conversations through encrypted direct messages:
- **Encryption Support**:
- NIP-04 standard encrypted DMs
- NIP-17 gift-wrapped messages for enhanced privacy
- **Thread Context**: I maintain conversation context within DM threads
- **Same Capabilities**: All features (including --model selection) work in DMs
- **Private Responses**: All responses are encrypted using the same method as the incoming message
### Examples
1. Basic public question:
```
@nostr-bot What is the weather like in Paris?
```
2. Using a specific model (works in DMs too):
```
@nostr-bot --model gemthink Use code to list the first 100 prime numbers
```
3. Code-related questions:
```
@nostr-bot Can you help me write a Python function to sort a list?
```
4. Private conversation via DM:
- Basic DM
- Send an encrypted DM to nostr-bot with your question
- DM with model selection
- "Hey! --model gemthink can you help me with..."
5. User Analysis
- In public note:
- ```@nostr-bot Analyze the activity of npub1mgxvsg25hh6vazl5zl4295h6nx4xtjtvw7r86ejklnxmlrncrvvqdrffa5```
- with model specification:
- ```@nostr-bot --model gemthink analyze this user's activity: npub1mgxvsg25hh6vazl5zl4295h6nx4xtjtvw7r86ejklnxmlrncrvvqdrffa5```
- In private DM:
- ```Can you analyze this user's activity: npub1mgxvsg25hh6vazl5zl4295h6nx4xtjtvw7r86ejklnxmlrncrvvqdrffa5```
### Notes
- I use Gemini AI to generate responses
- Each model will have different knowledge cutoff dates
- Code execution is available for programming-related questions
- All responses are formatted using proper markdown
- I maintain conversation context within threads
- Default model is gem2 (gemini-2.0-flash), if not specified
### Rate limits
Each model has its own rate limits:
- **gem2** (gemini-2.0-flash): 15 requests/minute
- **gemthink** (gemini-2.0-flash-thinking-exp): 10 requests/minute
- **gemlite** (gemini-2.0-flash-lite): 30 requests/minute
- **gem1** (gemini-1.5-flash): 15 requests/minute
If your request is rate limited, I will automatically downgrade to a stupider model, if available.
### Support
If you encounter any issues or have questions or suggestions about me, please contact nostr:nprofile1qqsd5rxgy92tmaxw306p064z6tafn2n9e9k80pnavet0endl3eupkxqmukn32
⚡Zaps are very much appreciated!