Claude Skill
open-compress/claw-compactor
Open-source tool to compress LLM tokens & cut AI agent costs by up to 97%. 5-layer context compression for OpenClaw. Deterministic, no LLM needed. Save tokens, optimize prompts.
Overview
Stars2,124
Forks164
LanguagePython
Last pushed2026-03-21
Last synced2026-03-29
Repository
Owneropen-compress
Repositoryclaw-compactor
Full nameopen-compress/claw-compactor
Repo ID1,154,042,797
🚀 Install this Skill
openclaw install open-compress/claw-compactorSummary
Claw Compactor is a deterministic LLM token compression and reduction tool designed to cut AI agent token costs by up to 97%. It provides a 5-layer context compression solution specifically for OpenClaw workspaces, enabling token saving, prompt compression, and context window optimization without requiring an LLM.
Chinese description
🦞 LLM 令牌压缩与精简工具 —— 将AI智能体令牌成本降低高达97%。专为OpenClaw工作空间设计的5层上下文压缩方案。采用确定性算法，无需依赖LLM。实现令牌节省、提示词压缩与上下文窗口优化。
Key features
- Deterministic token compression (no LLM required)
- Up to 97% reduction in AI agent token costs
- 5-layer context compression for OpenClaw workspaces
- Optimizes context window and reduces prompt size
- Focus on token saving and cost reduction
Use cases
- Reducing operational costs for AI agents and Claude Skill
- Compressing prompts to fit within context limits
- Optimizing OpenClaw workspace memory usage
- Managing token budgets for large-scale AI deployments
- Improving efficiency of context-heavy AI applications
Topics
ai-agent-toolsai-infrastructureast-code-analysisclaw-compactorcontext-compressioncontext-pruningcontext-window-optimizationdeveloper-toolsfusion-pipelinellm-compressionllm-context-compressionllm-cost-reductionllm-token-compressionllm-toolsopenclawprompt-compressionpythonreversible-compressiontoken-compressiontree-sitter