sqz MCP Server
ojuschugh1/sqz
[](https://agentrank-ai.com/tool/ojuschugh1--sqz/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) 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.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
ojuschugh1/sqz is a Rust tool licensed under Apache-2.0. 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. Topics: cli, llms, rust, tokens, agentic-ai, cost-optimization, developer-tools, open-source, token-optimization, ai-agents, claude-code, codex, coding-agents, context-compression, context-window, cursor, llm, mcp, mcp-server, prompt-caching.
Ranked #137 out of 24846 indexed tools.
In the top 1% of all indexed tools.
Ecosystem
Score Breakdown
647 stars → growing community
Last commit 1mo ago → moderate activity
27/29 issues closed → responsive maintainer
8 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/ojuschugh1--sqz/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/ojuschugh1--sqz/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/ojuschugh1--sqz" alt="AgentRank"></a> Matched Queries
From the README
<p align="center">
<pre>
███████╗ ██████╗ ███████╗
██╔════╝██╔═══██╗╚══███╔╝
███████╗██║ ██║ ███╔╝
╚════██║██║▄▄ ██║ ███╔╝
███████║╚██████╔╝███████╗
╚══════╝ ╚══▀▀═╝ ╚══════╝
</pre>
</p>
<p align="center">
<strong>Pre-injection context compression and session deduplication for AI coding agents</strong>
</p>
<p align="center">
<sub>
<strong>Real session stats:</strong>
3,003 compressions ·
<strong>178,442 tokens saved</strong> ·
24.7% avg reduction · up to
<strong>92%</strong> on output the model already has
</sub>
</p>
<p align="center">
<a href="https://thenextgentechinsider.com/pulse/sqz-tool-cuts-llm-token-use-by-92-for-file-heavy-ai-tasks"></a>
<a href="https://hysenlabs.com/en/projects/ojuschugh1-sqz"></a>
</p>
<p align="center">
<a href="https://crates.io/crates/sqz-cli"></a>
<a href="https://www.npmjs.com/package/sqz-cli"></a>
<a href="https://pypi.org/project/sqz/"></a>
<a href="https://marketplace.visualstudio.com/it Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.