PySpur - AI Agents Builder

demo.mp4

✨ Core Benefits

1. Drag-and-drop AI Agents Builder:
   • High-level, batteries-included prompting techniques (MCTS, Self-Refinement, BoN, ToT, etc.)
   • Low-level primitives for parallel/sequential sampling (loops, if-else, merge branches)
   • Verifiers (Code nodes, LLM-as-a-judge, software integrations, etc.)
2. Debug with Evals Visualizer:
   • Common reasoning benchmarks (GSM8k, MATH, ARC, etc.)
   • Scorers via LLM-as-a-judge
   • Custom datasets via CSV, JSONL, HF Datasets
3. One-Click Deployment of a Batch Inference API:
   • Self-hosting of async batch APIs for full flexbility
   • Submit/manage batch jobs via UI for ease of use
   • Fault tolerance and job persistence for long-running jobs

🕸️ Why PySpur?

• Easy-to-hack, eg., one can add new workflow nodes by simply creating a single Python file.
• JSON configs of workflow graphs, enabling easy sharing and version control.
• Lightweight via minimal dependencies, avoiding bloated LLM frameworks.

🗺️ Roadmap

• Canvas
• Async/Batch Execution
• Evals
• Spur API
• New Nodes
  • LLM Nodes
  • If-Else
  • Merge Branches
  • Tools
  • Loops
• Pipeline optimization via DSPy and related methods
• Templates
• Compile Spurs to Code
• Multimodal support
• Containerization of Code Verifiers
• Leaderboard
• Generate Spurs via AI

Your feedback will be massively appreciated. Please tell us which features on that list you like to see next or request entirely new ones.

⚡ Quick start

You can get PySpur up and running in three quick steps.

1. Clone the repository:

   git clone https://github.com/PySpur-com/PySpur.git
   cd pyspur

2. Start the docker services:

   sudo docker compose up --build -d

   This will start a local instance of PySpur that will store spurs and their runs in a local SQLite file.

3. Access the portal:

   Go to http://localhost:6080/ in your browser.

   Enter pyspur/canaryhattan as username/password.