psygen-revised

Python package implementing Psygen Revised: a three-stage (optional fourth) LLM pipeline that produces a structured psychological profile for a character from a natural-language query.

• Schema: JSON Schema for each layer and the merged profile (package data).
• Runner: ProfileGenerator chains axiom → intermediate → emergent calls, validates JSON, merges evidence.
• Prompt surface: to_prompt_string() emits dialogue-ready text (20 emergent traits + coping style + role identity), capped at 600 characters per the design contract.

Install

pip install psygen-revised

With OpenAI client helper:

pip install psygen-revised[openai]

Quick use

import asyncio
from psygen_revised import ProfileGenerator, OpenAiLlmClient

async def main():
    client = OpenAiLlmClient.from_env()  # OPENAI_API_KEY
    gen = ProfileGenerator(client)
    profile = await gen.generate("Linus from Stardew Valley")
    print(profile.to_prompt_string())
    print(profile.to_json())

asyncio.run(main())

Custom LLM backend

Implement psygen_revised.protocols.LlmClient (complete(system, user) -> str) and pass it to ProfileGenerator.

CLI

psygen-generate "Linus from Stardew Valley" -o linus.json

Design

See DESIGN.md and PLAN.md in this directory.

License

MIT