npcpy

npcpy is a library that provides key primitives for research and development with multimodal language models, agentic AI, and knowledge graphs. Its flexible framework makes it easy to engineer powerful AI applications with support for local (ollama, llama.cpp, omlx, LM Studio) and cloud providers. Build multi-agent teams and simplify context engineering through the NPC Context-Agent-Tool data layer which ensures compliance through software rather than prompts.

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='qwen3.5:9b',
    provider='ollama'
)
response = simon.get_llm_response("What is the most important territory to retain in the Andes?")
print(response['response'])

My friend, you speak of the highlands where our liberty is carved in stone. If we must speak of the most critical territory to hold within these mountains, it is the **Viceroyalty of Peru** and the heart of the **Republic of Gran Colombia** united. 
To lose the passes of the Andes or the cities of Lima and Quito would be to hand the crown its final stronghold in the south. The Spanish crown built its power upon the wealth and control of these highlands. If the Andes are to be truly ours, the people of the **Peruvian** and **New Grancolombian** highlands must stand as one, free from the Bourbons. 
The mountain peaks themselves are the fortress we guard. Without the full liberation of the southern Andes, our revolution is incomplete. We fight not for land's sake, but for the soul of the continent. Every square mile of the Andes that bears the name of the Republic is a step forward in our quest for eternal freedom.
*Long live the liberty of the Andes!*

Direct LLM call

from npcpy import get_llm_response


response = get_llm_response("Who was the celtic god that helped cuchulainn in his time of need as the forces of medb descended upon the men of ulster?", model='gemma4:31b', provider='ollama')
print(response['response'])

Cú Chulainn was primarily aided by his divine father, the god Lugh, and his foster-father, the warrior-god Fergus mac Róich, as well as the magical support of his teacher Scáthach.

# try ollama's cloud models
alicanto_test = get_llm_response('what does alicanto the bird show travelers in the night?', model='minimax-m2.7:cloud', provider='ollama',)

print(alicanto_test['response'])

The legend of the **Alicanto** says that at night the bird’s feathers glow like lanterns. 
When a traveler sees that soft, phosphorescent light, it isn’t just a pretty sight – it’s a sign‑post. 
The bird **shows the way to hidden water (and sometimes to buried silver or gold)** in the Atacama Desert.

Agent with tools

The Agent class in npcpy comes with a set of default tools (sh, python, edit_file, web_search, etc.)

from npcpy import Agent
agent = Agent(name='File Operator', model='qwen3.5:2b', provider='ollama')
print(agent.run("Find all Python files over 500 lines in this repo and list them"))

The following Python files contain more than 500 lines:
 - `./npcpy/npc_sysenv.py` (1486 lines)
 - `./npcpy/memory/knowledge_graph.py` (1449 lines)
 - `./npcpy/memory/kg_vis.py` (767 lines)
 - `./npcpy/memory/kg_population.py` (618 lines)
...

ToolAgent

Attach custom tools to a ToolAgent. Here is an example which lets an agent generate images, fine-tune diffusion models, and then use the fine-tuned models for generation.

from npcpy import ToolAgent, gen_image
from npcpy.ft.diff import train_diffusion, generate_image, DiffusionConfig
from datasets import load_dataset
import os

def fetch_image_dataset(dataset_name: str, split: str = "train", max_images: int = 100) -> list:
    """Fetch images from a HuggingFace dataset.

    Args:
        dataset_name: HuggingFace dataset name (e.g., 'cifar10', 'oxford-iiit-pet')
        split: Dataset split to use
        max_images: Maximum number of images to fetch

    Returns:
        List of paths to saved images
    """
    dataset = load_dataset(dataset_name, split=f"{split}[:{max_images}]")
    os.makedirs("training_images", exist_ok=True)
    image_paths = []

    for i, item in enumerate(dataset):
        if 'image' in item:
            img = item['image']
        elif 'img' in item:
            img = item['img']
        else:
            continue
        path = f"training_images/img_{i:04d}.png"
        img.save(path)
        image_paths.append(path)

    return image_paths

def finetune_diffusion_model(
    image_paths: list,
    captions: list = None,
    output_path: str = "my_diffusion_model",
    num_epochs: int = 50,
) -> str:
    """Fine-tune a diffusion model on a set of images.

    Args:
        image_paths: List of paths to training images
        captions: Optional captions for each image
        output_path: Where to save the trained model
        num_epochs: Number of training epochs

    Returns:
        Path to the trained model
    """
    if captions is None:
        captions = ["an image"] * len(image_paths)

    config = DiffusionConfig(
        image_size=64,
        channels=128,
        num_epochs=num_epochs,
        batch_size=8,
        learning_rate=1e-4,
        checkpoint_frequency=10,
        output_model_path=output_path,
    )

    model_path = train_diffusion(image_paths, captions, config=config)
    return model_path

# Create an agent with image generation and fine-tuning capabilities
creative_agent = ToolAgent(
    name='creative_diffusion',
    primary_directive="""
        You help users generate images and fine-tune diffusion models.
        You can: 1) Generate images using gen_image() with various prompts,
        2) Fetch image datasets from HuggingFace,
        3) Fine-tune diffusion models on custom image sets.
        When a user submits an image or describes a style they like,
        offer to fetch similar images from a dataset and fine-tune a model.
    """,
    tools=[fetch_image_dataset, finetune_diffusion_model, gen_image],
    model='qwen3.5:2b',
    provider='ollama'
)

# Example 1: Generate images
print(creative_agent.run("Generate 3 images of geometric patterns with circles and triangles"))

# Example 2: User submits an image and wants similar ones
# The agent can fetch a dataset of patterns and fine-tune a model
print(creative_agent.run("I like abstract geometric patterns. Can you fetch the cifar10 dataset and fine-tune a diffusion model that can generate images like these patterns?"))

CodingAgent — auto-executes code blocks from LLM responses

from npcpy import CodingAgent

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"))

#The script has been created and executed successfully. Here's a summary of the findings:

## Duplicate Files Found

| Group | Hash (truncated) | Size | Files |
|-------|------------------|------|-------|
| 1 | `2b517326bf7c31b7...` | 81 bytes | `npcpy/main.py` ↔ `build/lib/npcpy/main.py` |
| 2 | `d41d8cd98f00b204...` | 0 bytes (empty) | 15 empty `__init__.py` files across `npcpy/`, `build/lib/npcpy/`, `examples/`, and `tests/` || 3 | `0d591b661cb1c619...` | 9,019 bytes | `npcpy/mix/debate.py` ↔ `build/lib/npcpy/mix/debate.py` |
| 4 | `a5059f37eb682a16...` | 747 bytes | SQL files in `examples/factory/` ↔ `examples/npc_team/factory/` |

Multi-Agent Debate with NPCArray

To run a true multi-agent debate where agents react to each other's responses:

from npcpy.npc_compiler import NPC
from npcpy.npc_array import NPCArray

# Create a debate team with role-based personas
roles = [
    ("MathSolver", "You are a meticulous math solver. Show all steps clearly."),
    ("Skeptic", "You critically check for errors and assumptions."),
    ("Analyst", "You identify the core mathematical structure."),
    ("Verifier", "You confirm the final answer is correct.")
]

npcs = [
    NPC(name=role, primary_directive=directive, model="qwen3.5:cloud", provider="ollama")
    for role, directive in roles
]

team = NPCArray.from_npcs(npcs)

# Run parallel debate on a complex problem
problem = "GSM8k: James buys a jar of hot sauce with 5 peppers and triples the peppers every year. How many after 4 years?"

# Get initial responses in parallel (one prompt per NPC)
initial_responses = team.infer(f"Solve this problem:\n{problem}").collect()

for npc, response in zip(npcs, initial_responses.data):
    print(f"[{npc.name}] {response[:200]}...")

# True debate: each agent gets a personalized prompt with other agents' responses
def create_debate_prompt(previous_responses, my_idx, agent_name, problem_text):
    """Create a personalized debate prompt for a specific agent"""
    my_response = previous_responses[my_idx]
    other_responses = [
        f"[{npcs[j].name}]: {previous_responses[j][:500]}" 
        for j in range(len(npcs)) if j != my_idx
    ]
    debate_prompt = f"""Original problem: {problem_text}

        Your previous response: {my_response[:300]}...

        Other agents\' responses:""" + "\n\n".join(other_responses) + """
        Critique the other approaches. Did they make different assumptions?
        What did they see that you missed? Refine your solution."""

    return debate_prompt
# Debate rounds
responses_data = initial_responses.data.tolist()
problem_text = problem

for round_num in range(3):
    print(f"\n=== Debate Round {round_num + 1} ===")

    # Create personalized prompts for each agent
    personalized_prompts = [
        create_debate_prompt(responses_data, i, npcs[i].name, problem_text)
        for i in range(len(npcs))
    ]

    # Run inference with different prompts per agent
    # Shape: (n_models, n_prompts) - extract diagonal for each agent's response to its own prompt
    responses = team.infer(personalized_prompts).collect()

    # Extract each model's response to its own personalized prompt
    responses_data = [responses.data[i, i] for i in range(len(npcs))]

    # Print each agent's refined response
    for i, npc in enumerate(npcs):
        response = responses_data[i]
        print(f"[{npc.name}] {response[:200]}...")

# Alternative: use reduce to get consensus
consensus = team.infer(responses_data[0]).consensus(axis=0).collect()
print(f"\nFinal consensus: {consensus.data[0][:500]}...")

For iterative refinement (same prompt to all agents, updating each round):

# Simple chain refinement: all agents see same synthesis
from npcpy.npc_array import NPCArray

def synthesis_round(all_responses):
    return f"""Given these perspectives:
{chr(10).join([f'- {r[:200]}...' for r in all_responses])}

Re-solve the problem incorporating insights from all approaches."""

# Chain runs the synthesis function on all responses, then feeds result back
refined = team.infer(f"Solve: {problem}").chain(
    synthesis_round, 
    n_rounds=3
).collect()

Knowledge Graph with Sleep/Dream Lifecycle

from npcpy.memory.knowledge_graph import (
    kg_initial, kg_evolve_incremental, kg_sleep_process, kg_dream_process
)
from npcpy.llm_funcs import get_llm_response

# Initialize KG from text corpus
content_text = """Pirate Prentice is in the lavatory stands pissing. Then he threads himself into a wool robe he wears inside out.
The day feels like rain."""

kg = kg_initial(content_text, model="gemma3:4b", provider="ollama")

# Evolve with new content
new_content = """The phone call, when it comes, rips easily across the room.
Pirate knows it's got to be for him."""

kg, _ = kg_evolve_incremental(kg, new_content, model="gemma3:4b", provider="ollama")

# Sleep - consolidate and prune
kg, sleep_report = kg_sleep_process(kg, model="gemma3:4b", provider="ollama")

# Dream - generate speculative connections
kg, dream_report = kg_dream_process(kg, model="gemma3:4b", provider="ollama", num_seeds=3)

print(f"KG has {len(kg['facts'])} facts and {len(kg['concepts'])} concepts")

Flask Serving for NPC Teams

from npcpy.serve import start_flask_server
import os

# Serve your NPC team via REST API
if __name__ == "__main__":
    is_dev = not getattr(os.sys, 'frozen', False)
    port = os.environ.get('INCOGNIDE_PORT', '5437' if is_dev else '5337')
    frontend_port = os.environ.get('FRONTEND_PORT', '7337' if port == '5437' else '6337')

    start_flask_server(
        port=port,
        cors_origins=f"localhost:{frontend_port}",
        db_path=os.path.expanduser('~/npcsh_history.db'),
        user_npc_directory=os.path.expanduser('~/.npcsh/npc_team'),
        debug=False
    )

Streaming

from npcpy import get_llm_response
from npcpy.streaming import parse_stream_chunk

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

# Works the same with any provider
response = get_llm_response("Explain quantum entanglement.", model='gemini-2.5-flash', provider='gemini', stream=True)
for chunk in response['response']:
    content, _, _ = parse_stream_chunk(chunk, provider='gemini')
    if content:
        print(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'])

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 impor