Interested to stay in the loop and to hear the latest and greatest about npcpy ? Be sure to sign up for the npcpy newsletter!
Welcome to npcpy, the python library for the NPC Toolkit and the home of the core command-line programs that make up the NPC Shell (npcsh).
npcpy is an agent-based framework designed to easily integrate AI models into one's daily workflow and it does this by providing users with a variety of interfaces through which they can use, test, and explore the capabilities of AI models, agents, and agent systems.
Getting Started
- Installation - System dependencies and pip install options
- Quickstart - Get your first response in 5 steps
- Core Concepts - NPC, Team, Jinx, Provider, NPCArray explained
Guides
- Working with LLMs - get_llm_response, streaming, JSON, messages, attachments
- Building Agents - NPC creation, directives, tools
- Multi-Agent Teams - Team orchestration with forenpc coordination
- Jinx Workflows - Jinja Execution templates for multi-step prompt pipelines
- Skills - Knowledge-serving jinxes with progressive section disclosure
- NPCArray - Vectorized AI - NumPy-like operations over model populations
- Image, Audio & Video - Generation with Ollama, diffusers, OpenAI, Gemini
- Knowledge Graphs - Build and evolve knowledge graphs from text
- Fine-Tuning & Evolution - SFT, RL, diffusion, genetic algorithms
- Serving & Deployment - Flask server and REST API
- ML Functions - Scikit-learn grid search, ensemble prediction
- Building Applications - Database persistence, memory, NPCSQL, desktop automation, triggers
Reference
- Architecture - NPC data layer overview
- API Reference - Auto-generated API docs
Contributing
Contributions are welcome! Please submit issues and pull requests on the GitHub repository.
Support
If you appreciate the work here, consider supporting NPC Worldwide with a monthly donation, buying NPC-WW themed merch, or hiring us to help you explore how to use npcpy and AI tools to help your business or research team, please reach out to info@npcworldwi.de .
Incognide
There is a graphical user interface that makes use of the NPC Toolkit through Incognide. See the source code for Incognide here. Download the executables at our website.
License
This project is licensed under the MIT License.