open-compressopen-compressOfficialยท2 Agent Skills Included

claw-compactor

Cut AI token costs by compressing code, logs, and conversations

Compresses code, JSON, logs, diffs, and chat history into smaller token payloads before sending them to AI models. Eliminates wasted API spend on bloated prompts, duplicate content, and oversized context windows. Runs 14 content-aware compression stages locally with zero LLM inference cost, and stores originals for full reversibility. Includes benchmarks and a live memory engine so agents keep long-term context at a fraction of the price.
npx skills add open-compress/claw-compactor --all -g -y

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install Claw Compactor?โ–ผ

Run `npx skills add open-compress/claw-compactor --all -g -y` in your terminal to install the full skill suite globally.

How to reduce LLM token costs?โ–ผ

Claw Compactor shrinks prompts, code, and chat history by 15โ€“82% before they reach the model, directly lowering your API bill.

Does compression lose important information?โ–ผ

No. It uses content-aware stages that protect code identifiers and JSON structure, and a Rewind store lets the AI retrieve any original section on demand.

Does Claw Compactor work with AI coding agents?โ–ผ

Yes. It follows the SKILL.md standard and integrates with OpenClaw, Claude Code, and similar agents, including automatic memory compression for long sessions.

Do I need a GPU or paid model to run it?โ–ผ

No. The core pipeline runs locally in under 50ms with zero dependencies and no LLM inference cost.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’