# NPC-Worldwide/npcpy

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Repository: https://github.com/NPC-Worldwide/npcpy
Canonical: https://ross.abutalabs.com/products/npcpy
Language: Python
License: MIT
License Family: permissive
Topics: agents, ai, llm, python, sql, yaml, ollama, perplexity, mcp, mcp-client, mcp-server
Last push: 2026-08-26T04:26:11+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 50
- inputs: {"age_days": 705, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 307}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1480, forks 114 (observed 2026-08-28T04:04:50.611542+00:00)

## What it is
npcpy is a Python library providing primitives for building applications with multimodal LLMs, agentic AI, and knowledge graphs. It supports local model providers like Ollama and llama.cpp as well as cloud providers, and includes an NPC Context-Agent-Tool data layer for building multi-agent teams.

## Use cases
- build multi-agent AI teams in python
- run local LLMs with ollama from python
- create LLM personas with directives
- integrate LLMs into python applications
- build knowledge graphs with agents
- connect to MCP servers and tools
- experiment with agentic AI workflows

## When to choose
- you want a flexible python library for LLM and agent development
- you need support for both local and cloud model providers
- you want to build multi-agent systems with structured context management
- you want MIT-licensed tooling for AI research and prototyping

## When to avoid
- you need a production-ready managed agent platform rather than a library
- you only need simple single-shot LLM API calls with no agent features
- you work outside the Python ecosystem

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-inference, rag, mcp, chatbot, nlp, machine-learning
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: llm-agents, knowledge-graphs, ollama, multi-agent, personas, context-engineering, mcp-client, mcp-server, ai-agents, natural-language-processing

## Member repositories
- NPC-Worldwide/npcpy (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:50.611542+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:12.935218+00:00, confidence not recorded.
  - readme: https://github.com/NPC-Worldwide/npcpy (fetched 2026-08-28T04:04:50.611542+00:00, sha c15a7b6ac05e)
  - registry_pypi: https://pypi.org/pypi/npcpy/json (fetched 2026-08-29T11:41:06.322089+00:00, sha 4a4d00b81603)
- Data as of 2026-08-30T08:39:29.467469+00:00.