Sqz
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,…
sqz compresses tool output before it enters the model’s context window. sqz runs as a hook and an MCP server for multiple AI coding clients. sqz is deterministic, offline, and every compressed result can be recovered byte-exact.
sqz provides a stats report showing what it saved per command from your own sessions. sqz includes a doctor command that verifies the whole compression chain and client routing. Across 3,003 real compressions sqz saved 178,442 tokens, a 24.7% average reduction.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.