sqz vs token-squeezer

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

Compresses large blocks of text, code, or conversation history into hyper-dense Reasoning Maps optimized for LLM context windows. Saves agents 80%+ on token costs. Stateless. Pay $0.001 USDC per compression via x402 on Base network.

MCP Servers

Models

—

—

—

Rust

—

NOASSERTION

—

—

—

18

0

0