npcpy
A Python library for NLP, multimodal LLMs, agent AI, ML, and knowledge graph research.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 1.4k
- Source
- mcp-github
- Repository
- github.com/NPC-Worldwide/npcpy
Overview
npcpy provides essential primitives for research and development of multimodal language models, agent AI, and knowledge graphs. Its flexible framework makes building powerful AI applications easy, supporting both local (e.g., ollama, llama.cpp) and cloud providers. The NPC Context-Agent-Tool data layer simplifies context engineering and ensures compliance. Suitable for researchers and developers working on natural language processing, multimodal large model training, and knowledge graph construction.
Capabilities
- ▪Create and use roles
- ▪Directly invoke LLMs
- ▪Integrate agent tools
- ▪Generate and fine-tune diffusion models
Use cases
Setup
pip install npcpy
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How to install npcpy?
Use the pip command: pip install npcpy
Which models does npcpy support?
Supports a variety of models from local and cloud providers, such as qwen3.5:9b, gemma4:31b, etc.
Related skills
pstack-claude
Provides rigorous workflows for multiple agents, supporting Claude Code, Codex, and more.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.