Lossless Claw Helper

Lossless Context Management plugin for OpenClaw, based on the LCM paper. It 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.

What It Does

When a conversation grows beyond the model's context window, OpenClaw normally truncates older messages. LCM instead:

1. Persists every message in a SQLite database, organized by conversation.
2. Summarizes older message chunks using the configured LLM.
3. Condenses summaries into higher-level nodes, forming a DAG.
4. Assembles each turn from summaries plus recent raw messages.
5. Exposes retrieval tools so agents can search and recall details from compacted history.

Nothing is lost: raw messages remain in the database, summaries link to source material, and agents can drill into compacted history.

Quick Start

Prerequisites