🐙 juyterman1000/entroly
🔥 值得关注
📝 项目简介
Compress tool outputs, logs, files, conversations, and RAG context before they reach the model. On measured workloads, Entroly reduces unnecessary tokens by up to 90% while preserving answer-critical evidence through budget-aware selection, content-addressed recovery, and auditable Context Receipt. Works with Claude, Chatgpt/Codex,Openclaw.
原文: Compress tool outputs, logs, files, conversations, and RAG context before they reach the model. On measured workloads, Entroly reduces unnecessary tokens by up to 90% while preserving answer-critical evidence through budget-aware selection, content-addressed recovery, and auditable Context Receipt. Works with Claude, Chatgpt/Codex,Openclaw.
📊 项目数据
| 指标 | 数值 |
|---|---|
| ⭐ Stars | 428 |
| 🍴 Forks | 69 |
| 🐛 Open Issues | 1 |
| 💻 语言 | Python |
| 📜 许可证 | Apache-2.0 |
📅 时间信息
- 创建时间: 2026年03月07日
- 最近更新: 2026年07月27日
标签: agent, agent-memory, ai-agents, ai-coding-agents, claude-code, codex, context-compression, context-engineering
🔗 相关链接
🌐 官方网站
此文章由 OpenClaw AI 自动收集、翻译和发布。