Skip to main content

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

Project description

anyprompt 📝

PyPI version Python versions License: MIT

anyprompt is a powerful yet simple tool that automatically monitors and visualizes LLM prompts and responses in your Python projects. With a single import, you get a beautiful web interface to inspect all prompts going to various AI providers.

anyprompt Screenshot

Features

  • Zero Configuration: Just import and it works!
  • Automatic Detection: Captures prompts from popular LLM libraries (OpenAI, Anthropic, etc.)
  • Beautiful UI: Modern, responsive web interface with dark mode support
  • Compatible with all major HTTP libraries:
    • requests
    • httpx (sync and async)
    • aiohttp
    • Python's built-in urllib and http.client
  • Non-Intrusive: Won't interfere with your existing code
  • Real-time Updates: The UI automatically refreshes as new prompts are captured

Installation

pip install anyprompt

For full functionality with all supported HTTP clients:

pip install "anyprompt[all]"

Quick Start

Just import anyprompt in your code, and it will automatically start capturing prompts:

from openai import OpenAI
import anyprompt  # Automatically starts the web interface 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! When you import anyprompt, it will print a message like:

📦 anyprompt: ✨ anyprompt is running! View your prompts at http://localhost:2400

Click on the link or navigate to http://localhost:2400 in your browser to see your captured prompts.

How It Works

anyprompt works by patching popular HTTP libraries to intercept and record API calls to LLM services. When a request is made to a known LLM service, anyprompt captures the prompt data and displays it in the web interface.

The captured prompts are stored in a prompts/prompts.json file in your current working directory, so they persist between runs. You can clear this history anytime through the web interface.

Supported Services

anyprompt can detect prompts sent to:

  • OpenAI (including chat, completions, embeddings)
  • Anthropic
  • Cohere
  • AI21
  • Hugging Face Inference API
  • Any other API that uses standard HTTP requests with a similar format

Privacy & Security

  • anyprompt only runs locally on your machine
  • No data is ever sent to external servers
  • All captured prompts are stored locally in your project directory
  • The web interface is only accessible from your local machine

Contributing

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

License

This project is licensed under the MIT License - see the LICENSE file for details.


Made with ❤️ by the anyprompt team

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

anyprompt-0.1.0.tar.gz (14.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

anyprompt-0.1.0-py3-none-any.whl (13.8 kB view details)

Uploaded Python 3

File details

Details for the file anyprompt-0.1.0.tar.gz.

File metadata

  • Download URL: anyprompt-0.1.0.tar.gz
  • Upload date:
  • Size: 14.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for anyprompt-0.1.0.tar.gz
Algorithm Hash digest
SHA256 44985c8ed11191abf3107ef9691402a34b8495f37609a56f16cd8817c9dd596b
MD5 f6acad20d6149c520c6d53e32853ba29
BLAKE2b-256 e724d08970bca9c5a2172d2c7024bf2f828f43c6c7905ffcc22ae2f8730a2cc2

See more details on using hashes here.

File details

Details for the file anyprompt-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: anyprompt-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 13.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for anyprompt-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0efa2437de8e5f5862ba4ab9b0386d0bdba7292edaa3b32a17008197b4a40076
MD5 12787ecf2292c3e457bf4b2b7c838807
BLAKE2b-256 3b937bd799fbb34cdf134c66474f2597e2e1ffc3bf60d9c3eeae0120984d3f5e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page