ai-agent

Sqz

Compress LLM context to save tokens and reduce costs
593 stars41 forksRustUpdated 6/21/2026100% free · open source
What it does

Compress large language model context to save tokens and reduce costs by removing unnecessary information

When to use it
  • When working with large language models that have high token usage
  • When trying to optimize costs for language model-based applications
  • When dealing with context windows that are too large to be efficiently processed
Ready-to-paste prompt
./target/release/sqz --input large_context.json --output compressed_context.json --ratio 0.5
Heads up: The sqz tool requires the Rust programming language and cargo package manager to be installed and configured on the system
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/sqz && curl -fsSL https://workflowstacks.com/api/skills/sqz/claude-skill -o ~/.claude/skills/sqz/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions
Details
Creator
ojuschugh1
Language
Rust
Category
ai-agent
Published
4/12/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.