PySpur is an AI agent builder designed to simplify the creation, execution, and debugging of AI agent workflows. It targets AI engineers seeking a Python-based solution with a visual, drag-and-drop interface.
Key features include:
- Drag-and-Drop Interface: Visually build and iterate on agents.
- Loops: Implement iterative tool calling with memory.
- File Upload: Process documents via file uploads or URLs.
- Structured Outputs: Define JSON schemas for structured data.
- RAG Support: Parse, chunk, embed, and manage data in vector databases.
- Multimodal Capabilities: Handle video, images, audio, text, and code.
- Tool Integration: Connect to Slack, Firecrawl, Google Sheets, GitHub, and more.
- Evaluation Framework: Evaluate agent performance on real-world datasets.
- One-Click Deployment: Publish agents as APIs.
- Python-Based: Extend functionality with custom Python nodes.
- Vendor Agnostic: Supports over 100 LLM providers, embedders, and vector DBs.
PySpur offers two primary deployment options:
- Python Package: Quick setup using
pip install pyspur. - Docker: Recommended for scalable, production-ready systems.
