Backed by Y Combinator

Improve your agents 10x faster

AI engineers use PySpur to improve AI agents without reinventing the wheel.

Open-Source Cloud Talk to founders

FROM LEADING AI INSTITUTIONS.

Problem

It takes a 1,000 tiny paper cuts to make AI reliable

Prompt Hell

Hours of prompt tweaking and trial-and-error frustration.

Workflow Blindspots

Lack of visibility into step interactions causing hidden failures and confusion.

Terminal Testing Nightmare

Squinting at raw outputs and manually parsing JSON.

Solution

A playground for agents that saves time

Step 1: Test Cases

Define test cases for the agent to execute

Step 2: Agentic Workflow

Build your agent in Python code or via drag-and-drop UI

Step 3: Iterate

Run tests, identify failures, and fix them quickly

Step 4: Deploy

Deploy your agent to the cloud or on-premise

Why PySpur?

Built for AI Engineers

Quick install

Install PySpur in seconds with pip.

bash

pip install pyspur

pyspur init my-project

pyspur serve --sqlite

Easy to add your own tools

Adding new tools is a matter of simply creating a single Python file.

python

class MyTool(DynamicSchemaNode):
    name = "my_tool"
    display_name = "MyTool"
    config_model = MyToolConfig

    async def run(self, input_data: MyToolInput) -> MyToolOutput:
        ...

Easy sharing and version control

Every agent can be exported as a JSON file. Share with your team, and commit to git.

json

{
  "name": "Research Idea Generator",
  "definition": {
    "nodes": [
      {
        "id": "research information",
        "title": "research information",
        "node_type": "InputNode",
        "config": {
          "output_schema": {
            "existing_method_name": "str",
            "existing_method_code": "str",
            "existing_method_paper": "str",
            "additional_hints": "str",
            "goals": "str",
            "constraints": "str"
          },
          "enforce_schema": false,
          "title": "research information"
        },
        "coordinates": {
          "x": 0,
          "y": 0
        }
      }
    ]
  }
}

Coming soon: SDKs for Python and TypeScript

Integrate with your existing codebase and tools.

python

from pyspur import Agent

agent = Agent(
    id="S32",
)

response = agent.run(
    messages=[{"company": "Microsoft", "goal": "Buy or sell?"}]
)

Pricing

Managed Service

MonthlyYearly

SANDBOX

Free/ month

For tinkerers and hobbyists

1 Team Member
10 Spurs
1GB Vector Storage
50 Documents
500 per day Message Requests

For tinkerers and hobbyists

Popular

TEAM

$699/ month

billed monthly

Unlimited Team Members
Unlimited Spurs
100GB Vector Storage
10k Documents
Unlimited Message Requests

Book a demo

For professional agent builders

ENTERPRISE

Talk to Sales