Llmcache

Name: Llmcache
Author: sp98

@sp98

リポジトリ

Llmcache について

Stop paying Claude to understand the same code it already understood yesterday.

基本情報

カテゴリ

その他

トランスポート

stdio

公開者

sp98

投稿者

Santosh Pillai

設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Llmcache?

Llmcache is an MCP server that caches AI-generated understanding of source code. It allows Claude to read each file once and reuse the cached understanding in subsequent sessions, saving tokens and money. It is for developers who repeatedly ask Claude to analyze the same codebases.

How to use Llmcache?

—

Key features of Llmcache

Caches AI-generated understanding of source code
Avoids re-reading the same files across sessions
Reduces token usage for Claude sessions
Saves costs by eliminating redundant analysis

Use cases of Llmcache

Repeatedly working with the same codebase across multiple Claude sessions
Reducing AI costs when analyzing large source files
Ensuring consistent understanding without re-scanning files

FAQ from Llmcache

What does Llmcache do?

Llmcache caches the understanding that Claude generates from your source code, so that subsequent sessions start from cached knowledge instead of reprocessing each file.

How does Llmcache save money?

By avoiding repeated analysis of the same code files, Llmcache reduces token consumption for Claude sessions, lowering usage costs.

What data is cached?

The AI-generated understanding of source code files is cached after the first read by Claude.

「その他」の他のコンテンツ

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K