Skip to content

tac0turtle/ai-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

optimizoor

AI optimization experiments. Each experiment is self-contained with its own pyproject.toml and uv environment — cd into the directory and uv run to get going.

Experiments

Experiment Description
prompt-compression Local prompt compression with LLMLingua-2 (BERT-based, ~500MB). FastAPI + browser UI.
prompt-proxy Transparent compression proxy for Claude Code & Codex. Rule-based structural transforms + LLMLingua-2 semantic compression with frozen/middle/hot zone architecture.
agent-memory Persistent agent memory via RAG + LanceDB + sentence-transformers. Extraction-first writes, time-weighted retrieval, MMR diversity, consolidation. CLI + FastAPI UI.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors