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
仓库信息
安装这个 Skill
npx vitestRegistry 信息
npx vitestnpx tsc --noEmitnpx 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。
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