$ loading_
Compress LLM text and JSON to reduce tokens and lower usage costs.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "TokenSqueezer LLM Token Compressor" MCP server from askskill: Run: claude mcp add 'io-github-pgalyen1987-tokensqueezer' -- npx -y @nodeproxy/tokensqueezer
Compress and recover local context for more efficient GPT/Codex token usage.
Compress LLM inputs like logs and RAG chunks to cut tokens.
Compress oversized JSON arrays into compact toon-style text to save tokens.
Compress outputs and context before LLMs to cut tokens without losing answers.
Analyze and compress Markdown to reduce tokens and improve AI efficiency.
Reduce token usage in Claude Code with automatic context optimization.