Search

Automatic token usage and cost tracking for the Anthropic SDK

Transform XLSX files into LLM-friendly semantic XML

Utilities for managing multi-shot conversations and structured data handling in LLM applications

Safely regenerate Cursor globalStorage telemetry fields in storage.json

Manage env-var caches on HPC clusters by syncing from slow persistent storage to fast scratch

Local GitHub Copilot API proxy — use GPT-4o, Claude, Gemini via OpenAI/Anthropic compatible APIs

Intelligent LLM router with task-aware routing, cost tracking, and observability

CLI for RefineX — AWS spot price arbitrage signals in your terminal

A visualisation tool for protein embeddings from pLMs

Pytest plugin for JavaScript coverage via Playwright CDP

Blazing-fast LLM token compression engine. Built in Rust. Reduce API costs 2-5x with mathematically provable zero quality loss.

RAG evaluation SDK — RAGの回答品質を3行で計測

AI-powered semantic keyword extraction using sentence embeddings and MMR

A Pythonic interface to LLMs.

Cut LLM reasoning-token costs by 60% with one line of code — pre-inference query difficulty routing.

Wyatt's Data Storage Format

A CLI supervisor for Claude Code sessions

A blazing-fast universal LLM gateway — call OpenAI, Anthropic, Gemini, Mistral & Ollama through one unified API.

A unified interface for multiple LLM providers

Convert web pages and HTML files to markdown and Claude XML formats