What it does
PySpur lets you build AI agents and workflows by connecting steps on screen, or in Python code. You can define test cases, run them and see what happened at each step.
It supports pauses that wait for a person to approve, loops, file uploads, structured outputs, document search (RAG) and tools like Slack and Google Sheets. It records traces of how deployed agents ran.
Its makers say it works with over a hundred AI providers, and a finished workflow can be published as an API, a doorway other programs can call.
Who it's for
AI engineers and developers who build and debug agent workflows.
Can I use it without coding?
With some setup. It's installed with Python and started with a command, then used in a browser. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Runs on
- Mac, Windows, Linux, Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
- Install PySpur with Python's package installer (Python 3.11 or newer).
- Create a new project and start the PySpur server.
- Open the local web page and add your AI provider keys in the API Keys tab.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- More on staying safe
Where people are talking about it
- Introduction to CUDA programming for Python developersHacker News · Feb 2025
- DeepSeek's multi-head latent attention and other KV cache tricksHacker News · Jan 2025