BlackHC/llm-strategy
Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types
Implements the Strategy Pattern by using LLM responses to satisfy abstract method contracts, with docstrings and type annotations automatically converted into structured prompts. Supports arbitrary dataclass return types and generic type variables, enabling meta-optimization workflows where LLMs iteratively refine hyperparameters based on task performance. Includes hyperparameter tracking and tracing infrastructure for collecting and analyzing LLM decision chains across multiple iterations.
401 stars and 45 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
401
Forks
24
Language
Python
License
MIT
Category
Last pushed
Mar 03, 2025
Monthly downloads
45
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/BlackHC/llm-strategy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
firattamur/llmdantic
Structured Output Is All You Need!
wsvincent/djangoforai
Django + local LLM + server side events + HTMX demo
Mgrsc/LLMQ-Horizon
Integrate LLM into QQ using Nonebot, LangChain, and LangGraph
sdsc-ordes/kg-llm-interface
Langchain-powered natural language interface to knowledge-graphs.
ls1intum/Pyris
An LLM microservice for the learning platform Artemis