npcpy

npcpy is a flexible agent framework for building AI applications and conducting research with LLMs. It supports local and cloud providers, multi-agent teams, tool calling, image/audio/video generation, knowledge graphs, fine-tuning, and more.

pip install npcpy

Quick Examples

Create and use personas

from npcpy import NPC

simon = NPC(
    name='Simon Bolivar',
    primary_directive='Liberate South America from the Spanish Royalists.',
    model='gemma3:4b',
    provider='ollama'
)
response = simon.get_llm_response("What is the most important territory to retain in the Andes?")
print(response['response'])

Direct LLM call

from npcpy import get_llm_response

response = get_llm_response("Who was the celtic messenger god?", model='qwen3:4b', provider='ollama')
print(response['response'])
# or use ollama's cloud models

test = get_llm_response('who is john wick', model='minimax-m2.7:cloud', provider='ollama',)

print(test['response'])

Agent with tools

from npcpy import Agent, ToolAgent, CodingAgent

# Agent — comes with default tools (sh, python, edit_file, web_search, etc.)
agent = Agent(name='ops', model='qwen3.5:2b', provider='ollama')
print(agent.run("Find all Python files over 500 lines in this repo and list them"))

# ToolAgent — add your own tools alongside defaults
import subprocess

def run_tests(test_path: str = "tests/") -> str:
    """Run pytest on the given path and return results."""
    result = subprocess.run(["python3", "-m", "pytest", test_path, "-v", "--tb=short"],
                            capture_output=True, text=True, timeout=120)
    return result.stdout + result.stderr

def git_diff(branch: str = "main") -> str:
    """Show the git diff against a branch."""
    result = subprocess.run(["git", "diff", branch, "--stat"], capture_output=True, text=True)
    return result.stdout

reviewer = ToolAgent(
    name='code_reviewer',
    primary_directive='You review code changes, run tests, and report issues.',
    tools=[run_tests, git_diff],
    model='qwen3.5:2b', provider='ollama'
)
print(reviewer.run("Run the tests and summarize any failures"))

# CodingAgent — auto-executes code blocks from LLM responses
coder = CodingAgent(name='coder', language='python', model='qwen3.5:2b', provider='ollama')
print(coder.run("Write a script that finds duplicate files by hash in the current directory"))

Streaming

from npcpy import get_llm_response

response = get_llm_response("Explain quantum entanglement.", model='qwen3.5:2b', provider='ollama', stream=True)
for chunk in response['response']:
    print(chunk.get('message', {}).get('content', ''), end='', flush=True)

JSON output

Include the expected JSON structure in your prompt. With format='json', the response is auto-parsed — response['response'] is already a dict or list.

from npcpy import get_llm_response

response = get_llm_response(
    '''List 3 planets from the sun.
    Return JSON: {"planets": [{"name": "planet name", "distance_au": 0.0, "num_moons": 0}]}''',
    model='qwen3.5:2b', provider='ollama',
    format='json'
)
for planet in response['response']['planets']:
    print(f"{planet['name']}: {planet['distance_au']} AU, {planet['num_moons']} moons")

response = get_llm_response(
    '''Analyze this review: 'The battery life is amazing but the screen is too dim.'
    Return JSON: {"tone": "positive/negative/mixed", "key_phrases": ["phrase1", "phrase2"], "confidence": 0.0}''',
    model='qwen3.5:2b', provider='ollama',
    format='json'
)
result = response['response']
print(result['tone'], result['key_phrases'])

Pydantic structured output

Pass a Pydantic model and the JSON schema is sent to the LLM directly.

from npcpy import get_llm_response
from pydantic import BaseModel
from typing import List

class Planet(BaseModel):
    name: str
    distance_au: float
    num_moons: int

class SolarSystem(BaseModel):
    planets: List[Planet]

response = get_llm_response(
    "List the first 4 planets from the sun.",
    model='qwen3.5:2b', provider='ollama',
    format=SolarSystem
)
for p in response['response']['planets']:
    print(f"{p['name']}: {p['distance_au']} AU, {p['num_moons']} moons")

Image, audio, and video generation

from npcpy.llm_funcs import gen_image, gen_video
from npcpy.gen.audio_gen import text_to_speech

# Image — OpenAI, Gemini, Ollama, or diffusers
images = gen_image("A sunset over the mountains", model='gpt-image-1', provider='openai')
images[0].save("sunset.png")

# Audio — OpenAI, Gemini, ElevenLabs, Kokoro, gTTS
audio_bytes = text_to_speech("Hello from npcpy!", engine="openai", voice="alloy")
with open("hello.wav", "wb") as f:
    f.write(audio_bytes)

# Video — Gemini Veo
result = gen_video("A cat riding a skateboard", model='veo-3.1-fast-generate-preview', provider='gemini')
print(result['output'])

Multi-agent team

from npcpy import NPC, Team

team = Team(team_path='./npc_team')
result = team.orchestrate("Analyze the latest sales data and draft a report")
print(result['output'])

Or define a team in code:

from npcpy import NPC, Team

coordinator = NPC(name='lead', primary_directive='Coordinate the team. Delegate to @analyst and @writer.')
analyst = NPC(name='analyst', primary_directive='Analyze data. Provide numbers and trends.', model='gemini-2.5-flash', provider='gemini')
writer = NPC(name='writer', primary_directive='Write clear reports from analysis.', model='qwen3:8b', provider='ollama')

team = Team(npcs=[coordinator, analyst, writer], forenpc='lead')
result = team.orchestrate("What are the trends in renewable energy adoption?")
print(result['output'])

Team from files

team.ctx:

context: |
  Research team for analyzing scientific literature.
  The lead delegates to specialists as needed.
forenpc: lead
model: qwen3.5:2b
provider: ollama
output_format: markdown
max_search_results: 5
mcp_servers:
  - path: ~/.npcsh/mcp_server.py

lead.npc:

#!/usr/bin/env npc
name: lead
primary_directive: |
  You lead the research team. Delegate literature searches to @searcher,
  data analysis to @analyst. Synthesize their findings into a coherent summary.
jinxes:
  - {{ Jinx('sh') }}
  - {{ Jinx('python') }}
  - {{ Jinx('delegate') }}
  - {{ Jinx('web_search') }}

searcher.npc:

#!/usr/bin/env npc
name: searcher
primary_directive: |
  You search for scientific papers and extract key findings.
  Use web_search and load_file to find and read papers.
model: gemini-2.5-flash
provider: gemini
jinxes:
  - {{ Jinx('web_search') }}
  - {{ Jinx('load_file') }}
  - {{ Jinx('sh') }}

Jinxes can reference a specific NPC to always run under that persona, and access ctx variables from team.ctx:

jinxes/search_and_summarize.jinx:

#!/usr/bin/env npc
jinx_name: search_and_summarize
description: Search for papers and summarize findings using the searcher NPC.
npc: {{ NPC('searcher') }}
inputs:
  - query
steps:
  - name: search
    engine: natural
    code: |
      Search for papers about {{ query }}.
      Return up to {{ ctx.max_search_results }} results.
  - name: summarize
    engine: natural
    code: |
      Summarize the findings in {{ ctx.output_format }} format:
      {{ output }}

The npc: field binds the jinx to a specific NPC — when this jinx runs, it always uses the searcher persona regardless of which NPC invoked it. Any custom keys in team.ctx (like output_format, max_search_results) are available as {{ ctx.key }} in Jinja templates and as context['key'] in Python steps.

my_project/
├── npc_team/
│   ├── team.ctx
│   ├── lead.npc
│   ├── searcher.npc
│   ├── analyst.npc
│   ├── jinxes/
│   │   └── skills/
│   └── models/
├── agents.md             # Optional: define agents in markdown
└── agents/               # Optional: one .md file per agent
    └── translator.md

.npc and .jinx files are directly executable:

./npc_team/lead.npc "summarize the latest arxiv papers on transformers"
./npc_team/jinxes/lib/sh.jinx bash_command="echo hello"

MCP server integration

Add MCP servers to your team for external tool access:

team.ctx:

forenpc: assistant
mcp_servers:
  - path: ./tools/db_server.py
  - path: ./tools/api_server.py

db_server.py:

from mcp.server.fastmcp import FastMCP

mcp = FastMCP("Database Tools")

@mcp.tool()
def query_orders(customer_id: str, limit: int = 10) -> str:
    """Query recent orders for a customer."""
    # Your database logic here
    return f"Found {limit} orders for customer {customer_id}"

@mcp.tool()
def search_products(query: str) -> str:
    """Search the product catalog."""
    return f"Products matching: {query}"

if __name__ == "__main__":
    mcp.run()

The team's NPCs automatically get access to MCP tools alongside their jinxes.

Agent definitions in markdown

agents.md — multiple agents in one file:

## summarizer
You summarize long documents into concise bullet points.
Focus on key findings, methodology, and conclusions.

## fact_checker
You verify claims against reliable sources and flag inaccuracies.
Always cite your sources.

agents/translator.md — one file per agent with optional frontmatter:

---
model: gemini-2.5-flash
provider: gemini
---
You translate content between languages while preserving tone and idiom.

Skills

Skills are knowledge-content jinxes that provide instructional sections to agents on demand.

npc_team/jinxes/skills/code-review/SKILL.md:

---
name: code-review
description: Use when reviewing code for quality, security, and best practices.
---
# Code Review Skill

## checklist

Npcpy

Install / Use

README