Prompt Cache Python Packages

replay-doctor

If the agent bill went up and nothing errored, a prompt cache broke. Replay Doctor names the turn it broke on, the cause, and the tokens re-billed at write prices. Reads Claude Code and Codex transcripts already on disk. Local Go CLI, zero third-party dependencies, no account, and no network request you did not type.

pion-vllm-mlx

Pion — the memory engine for AI inference

foldback-ai

Lossless context compression for LLM agents — fold it down, fold it back. Compresses tool outputs/logs before the model, prompt-cache-preserving, 39–82% fewer tokens. pip install foldback-ai

cachecheck

Find token accounting that silently undercounts Anthropic's prompt cache. Three rules, each from a defect found in a shipped agent framework.

codex-cache-monitor

A beautiful local terminal dashboard for Codex prompt cache visibility.