anyprompt 0.3.0

Automatically inspect and visualize LLM prompts and responses in your Python projects

📦
anyprompt

---

Installation

pip install anyprompt

What is anyprompt?

anyprompt is a lightweight tool that automatically captures and visualizes LLM prompts in your Python projects. With a single import, you get a beautiful web interface to inspect all communications with AI providers.

Quick Start

Just import and go!

from openai import OpenAI
import anyprompt  # Automatically starts at http://localhost:2400

client = OpenAI()

# This prompt will be automatically captured!
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Tell me a joke about programming"}]
)
print(response.choices[0].message.content)

That's it! Visit http://localhost:2400 in your browser to see your captured prompts.

Compatibility

Library	Status
browser-use	✅ Supported
langchain	✅ Supported
openai	✅ Supported
anthropic	✅ Supported
requests	✅ Supported
httpx	✅ Supported
aiohttp	✅ Supported
urllib	✅ Supported
http.client	✅ Supported

Advanced Examples

LangChain Integration

import anyprompt  # This automatically starts the anyprompt server

from langchain_openai import ChatOpenAI
from langchain.schema import HumanMessage

# Initialize the LLM
llm = ChatOpenAI(model="gpt-3.5-turbo")

# Make a call - anyprompt will automatically capture it
response = llm.invoke([HumanMessage(content="What's the capital of France?")])
print(response.content)

browser-use Integration

import anyprompt  # This automatically starts the anyprompt server

from langchain_openai import ChatOpenAI
from browser_use import Agent
import asyncio

async def main():
    agent = Agent(
        task="Compare the price of gpt-4o and DeepSeek-V3",
        llm=ChatOpenAI(model="gpt-4o"),
    )
    await agent.run()

asyncio.run(main())

Privacy & Security

• Runs locally on your machine
• No data sent to external servers
• All prompts stored locally in your project directory

⭐ Contributing

Contributions are welcome! Please feel free to submit a Pull Request.