Claude Skill

Martian-Engineering/lossless-claw

Lossless Claw 是 OpenClaw 的 TypeScript LCM 插件,为 Claude Skill 提供无损上下文管理。无数据丢失地保留 AI 对话历史。

概览

Stars4,854
Forks429
语言TypeScript
最后更新2026-07-02
最近同步2026-07-03
前往 GitHub

仓库信息

拥有者Martian-Engineering
仓库lossless-claw
完整名称Martian-Engineering/lossless-claw
Repo ID1,161,277,811

安装这个 Skill

npx vitest

Registry 信息

类型openclaw_skill
质量分85/100
验证状态readme_parsed
最近验证2026-05-29
平台
ClaudeOpenClaw
能力
pdfmemorysearchvideoterminal
识别文件
README.mddocspackage.jsontest
配置键
LCM_SUMMARY_BASE_URLURLPACKAGE_JSON
安装方式
  • npx vitest
  • npx tsc --noEmit
  • npx vitest test/engine.test.ts

项目简介

Lossless Claw 是一个基于 TypeScript 的 LCM(无损上下文管理)插件,专为 OpenClaw 设计,旨在在 AI 交互过程中无损保留和管理上下文。它确保跨会话的无缝上下文保持,提升 Claude Skill 工作流的可靠性。

英文描述

Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

要点

  • 跨会话的无损上下文保留
  • 与 OpenClaw 无缝集成
  • 基于 TypeScript,性能稳健
  • 针对 Claude Skill 工作流优化

使用场景

  • 在 AI 助手中维护对话历史
  • 确保多轮交互中的数据完整性
  • 支持复杂的 Claude Skill 自动化任务

README 摘要

# lossless-claw Lossless Context Management plugin for [OpenClaw](https://github.com/openclaw/openclaw), based on the [LCM paper](https://papers.voltropy.com/LCM) from [Voltropy](https://x.com/Voltropy). Replaces OpenClaw's built-in sliding-window compaction with a DAG-based summarization system that preserves every message while keeping active context within model token limits. ## Table of contents - [What it does](#what-it-does) - [Quick start](#quick-start) - [Configuration](#configuration) - [Commands And Skill](#commands-and-skill) - [Documentation](#documentation) - [Development](#development) - [License](#license) ## What it does Two ways to learn: read the below, or [check out this super cool animated visualization](https://losslesscontext.ai). When a conversation grows beyond the model's context window, OpenClaw (just like all of the other agents) normally truncates older messages. LCM instead: 1. **Persists every message** in a SQLite database, organized by conversation 2. **Summarizes chunks** of older messages into summaries using your configured LLM 3. **Condenses summaries** into higher-level nodes as they accumulate, forming a DAG (directed acyclic graph) 4. **Assembles context** each turn by combining summaries + recent raw messages 5. **Provides tools** (`lcm_grep`, `lcm_describe`, `lcm_expand`) so agents can search and recall details from compacted history Nothing is lost. Raw messages stay in the database. Summaries link back to their source messages. Agents can drill into any summary to recover the original detail. **It feels like talking to an agent that never forgets. Because it doesn't. In normal operation, you'll never need to think about compaction again.** ## Commands And Skill The plugin now ships a bundled `lossless-claw` skill plu

话题

暂无话题

探索更多

数据来自 GitHub,同步时间:2026-07-03