Martian-Engineering/lossless-claw

Registry

Summary

Lossless Claw is a TypeScript-based LCM (Lossless Context Management) plugin for OpenClaw, designed to preserve and manage context without data loss during AI interactions. It ensures seamless context retention across sessions, enhancing reliability for Claude Skill workflows.

Key features

• Lossless context preservation across sessions
• Seamless integration with OpenClaw
• TypeScript-based for robust performance
• Optimized for Claude Skill workflows

Use cases

• Maintaining conversation history in AI assistants
• Ensuring data integrity in multi-turn interactions
• Supporting complex Claude Skill automation tasks

README excerpt

# 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

Topics

No topics yet.