prompt-caching

ForthWrite is a Chrome extension for Gmail that learns a user’s email voice from sent messages and edits. This page explains its retrieval-and-feedback loop in detail, including pgvector-based RAG, edit-distance scoring, a phrasing miner, and the stack behind the product.

An interactive calculator for AI product unit economics. It models token costs, retries, prompt caching, model routing, infrastructure, support, and target gross margin, and can share scenarios through URL links.

Python library for managing LLM conversation history with cache-friendly message ordering, dynamic context, and compaction.

A VS Code blog post explaining how GitHub Copilot’s agentic harness is being optimized to reduce token usage, latency, and cost through extended prompt caching, tool search, and WebSocket connections.