---
title: "pyspur"
type: "tool"
slug: "pyspur-dev-pyspur"
canonical_url: "https://www.graphcanon.com/tools/pyspur-dev-pyspur"
github_url: "https://github.com/PySpur-Dev/pyspur"
homepage_url: "https://pyspur.dev"
stars: 5748
forks: 428
primary_language: "TypeScript"
license: "Apache-2.0"
categories: ["ai-agents", "developer-tools"]
tags: ["human-in-the-loop", "agents", "llm", "ai", "framework", "builder", "agent", "multimodal"]
updated_at: "2026-07-07T18:39:17.01824+00:00"
---

# pyspur

> A visual playground for iterating over AI agents faster.

PySpur is a tool designed to help AI engineers quickly and efficiently test, develop and iterate on their agents using both Python code and an intuitive user interface. It addresses common challenges such as prompt tuning, workflow visibility issues, and difficulty in evaluating agent outputs by providing a comprehensive solution for creating reliable agentic workflows.

## Facts

- Repository: https://github.com/PySpur-Dev/pyspur
- Homepage: https://pyspur.dev
- Stars: 5,748 · Forks: 428 · Open issues: 39 · Watchers: 48
- Primary language: TypeScript
- License: Apache-2.0
- Last pushed: 2026-06-29T17:53:12+00:00

## Categories

- [AI Agents](/categories/ai-agents.md)
- [Developer Tools](/categories/developer-tools.md)

## Tags

human-in-the-loop, agents, llm, ai, framework, builder, agent, multimodal

## Related tools

- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system (★ 226,962)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The self-improving AI agent built by Nous Research (★ 210,880)
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT: Build, Deploy, and Run AI Agents (★ 185,417)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659)
- [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019)
- [JavaGuide](/tools/snailclimb-javaguide.md) - Snailclimb/JavaGuide: 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发 (★ 156,863)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [dify](/tools/langgenius-dify.md) - Production-ready platform for agentic workflow development (★ 148,070)

## README (excerpt)

```text
<p align="center"><strong>Iterate over your agents 10x faster. AI engineers use PySpur to iterate over AI agents visually without reinventing the wheel.</strong></p>

<p align="center">
  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-blue"></a>
  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-blue"></a>
  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-blue"></a>
  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-blue"></a>
  <a href="./README_DE.md"><img alt="Deutsche Version der README" src="https://img.shields.io/badge/Deutsch-blue"></a>
<a href="./README_FR.md"><img alt="Version française du README" src="https://img.shields.io/badge/Français-blue"></a>
<a href="./README_ES.md"><img alt="Versión en español del README" src="https://img.shields.io/badge/Español-blue"></a>
</p>

<p align="center">
<a href="https://docs.pyspur.dev/" target="_blank">
  <img alt="Docs" src="https://img.shields.io/badge/Docs-green.svg?style=for-the-badge&logo=readthedocs&logoColor=white">
</a>
<a href="https://forms.gle/5wHRctedMpgfNGah7" target="_blank">
  <img alt="Cloud" src="https://img.shields.io/badge/Cloud-orange.svg?style=for-the-badge&logo=cloud&logoColor=white">
</a>
</p>

https://github.com/user-attachments/assets/54d0619f-22fd-476c-bf19-9be083d7e710

# 🕸️ Why PySpur?

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

AI engineers today face three problems of building agents: 

* **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.

We've been there ourselves, too. We launched a graphic design agent early 2024 and quickly reached thousands of users, yet, struggled with the lack of its reliability and existing debugging tools. 

## Solution: A playground for agents that saves time

### Step 1: Define Test Cases

https://github.com/user-attachments/assets/ed9ca45f-7346-463f-b8a4-205bf2c4588f
 
### Step 2: Build the agent in Python code or via UI

https://github.com/user-attachments/assets/7043aae4-fad1-42bd-953a-80c94fce8253

### Step 3: Iterate obsessively

https://github.com/user-attachments/assets/72c9901d-a39c-4f80-85a5-f6f76e55f473

### Step 4: Deploy

https://github.com/user-attachments/assets/b14f34b2-9f16-4bd0-8a0f-1c26e690af93

# ✨ Core features:

- 👤 **Human in the Loop**: Persistent workflows that wait for human approval.
- 🔄 **Loops**: Iterative tool calling with memory.
- 📤 **File Upload**: Upload files or paste URLs to process documents.
- 📋 **Structured Outputs**: UI editor for JSON Schemas.
- 🗃️ **RAG**: Parse, Chunk, Embed, and Upsert Data into a Vector DB.
- 🖼️ **Multimodal**: Support for Video, Images, Audio, Texts, Code.
- 🧰 **Tools**: Slack, Firecrawl.dev, Google Sheets, GitHub, and more.
- 📊 **Traces**: Automatically capture execution traces of deployed agents.
- 🧪 **Evals**: Evaluate agents on real-world datasets.
- 🚀 **One-Click Deploy**: Publish as an API and integrate wherever you want.
- 🐍 **Python-Based**: Add new nodes by creating a single Python file.
- 🎛️ **Any-Vendor-Support**: >100 LLM providers, embedders, and vector DBs.

# ⚡ Quick start

This is the quickest way to get started. Python 3.11 or higher is required.

1. **Install PySpur:**
    ```sh
    pip install pyspur
    ```

2. **Initialize a new project:**
    ```sh
    pyspur init my-project
    cd my-project
    ```
    This will create a new directory with a `.env` file.

3. **Start the server:**
    ```sh
    pyspur serve --sqlite
    ```
    By default, this will start PySpur app at `http://localhost:6080` using a sqlite database.
    We recommend you configure a postgres instance URL in the `.env` file to get a more stable experience.

4. **[Op
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/pyspur-dev-pyspur`](/api/graphcanon/tools/pyspur-dev-pyspur)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_