I build developer tools for AI agents, context optimization, and machine learning reproducibility. My work spans AI token optimization, agent harnesses, local RAG, computer vision, and NLP.

All repositories

Keep the signal. Cut the noise. Local CLI + MCP that folds verbose tool output for Claude Code, Codex, Cursor, and Claude Desktop — recoverable by reference.

• Folds passing tests, build progress, runner setup, and bulky JSON while keeping failures, assertions, and stack traces verbatim.
• Every cut is recoverable: the original stays in a local cache behind a usagetrim retrieve <ref> id. No model calls, nothing leaves the machine.
• Specialized filters for pytest, cargo, go, vitest, eslint, tsc, mypy, Docker, kubectl, terraform, gh JSON, and GitHub Actions logs.
• Lean MCP profiles (9–11 tools, 36–38% smaller schemas), targeted symbol reads, session dedup, and a gain report of local estimates.
• Optional native macOS pet showing remaining Codex/Claude allowance.

uv tool install usagetrim && usagetrim demo

Python Swift MCP Claude Code Codex Cursor Claude Desktop Context Engineering

Repository · Install · Demo · Connect your agent · Guide

Check whether a refactor or a coding agent's edit changed your experiment outputs.

• Screen selected reproducibility risks in scikit-learn, XGBoost, LightGBM, PyTorch, TensorFlow and Lightning, plus Python and NumPy RNGs. Static checks need no ML dependencies.
• Replay an experiment twice, then compare saved reports before and after an edit. Retain metrics, artifact hashes, commands and logs.
• Use the CLI, pre-commit hook, or reproducibility skill for coding agents.

Python ML reproducibility AST pre-commit

Quick demo — no ML dependencies · XGBoost training example — CPU · Install

The XGBoost example trains on a small synthetic dataset, accepts a refactor that preserves outputs, and reports changed outputs after reducing tree depth.

Local retrieval-augmented generation with Ollama embeddings, HNSW vector search, and optional FlagEmbedding reranking. The interactive CLI lets you compare answers with and without reranking.

Python Ollama HNSW FlagEmbedding uv

Shared skills, agent profiles and opt-in Git hooks for writing, debugging, PR review and releases. Generated versions support Codex, Claude Code, Cursor and OpenCode; Grok Bot uses manual setup. Start with Humanizer to edit a draft, or Skill Watch to track documentation changes and identify instructions needing review.

Python Markdown Skills Git hooks

Try Humanizer · Browse the workflows · Skill Watch demo

• Video Waste Dumping Detection — Video classification for the IWDD contest, with VideoMAE and X-CLIP training configurations. PyTorch Lightning

• Sudoku Solver — Grid extraction, digit recognition, and backtracking to solve Sudoku from images. PyTorch OpenCV

• Adaptive k for Classifier Selection — How dataset complexity relates to neighborhood size in dynamic classifier selection. scikit-learn DESlib

• GANs from Scratch — Vanilla GAN, DCGAN, and Conditional GAN on MNIST, CIFAR-10, and Fashion-MNIST. PyTorch Lightning Hydra

• T5 Text Summarizer — T5-small fine-tuning on CNN/DailyMail and XSum, with ROUGE evaluation and a demo UI. Transformers Gradio

• Emotube — YouTube comment sentiment analysis with filtering and interactive charts. FastAPI React PostgreSQL

Project screenshots and sample outputs

Ollama RAG: interactive CLI

Sudoku: solved puzzle

DCGAN: generated CIFAR-10 samples

T5: summarization interface

Emotube: application home page

GitHub activity