Submit a resource

Navigation

Back to directory

lossless-claw-enhanced

lossless-claw-enhanced is a deprecated fork of a context-management plugin for OpenClaw that replaces sliding-window compaction with a DAG-based summarization system preserving every message within the model's token limit.

Visit website (opens in a new tab)youtu.be
lossless-claw-enhanced

lossless-claw-enhanced is a Lossless Context Management plugin for the OpenClaw assistant, based on the LCM paper from Voltropy. It replaces OpenClaw's built-in sliding-window compaction with a DAG-based summarization system that keeps every message accessible while staying within a model's token limit.

The fork's two original contributions were CJK-aware token estimation, which corrects an upstream bug that undercounted Chinese, Japanese and Korean text by two to four times, and a CJK trigram full-text search. Both have since been merged into the upstream Martian-Engineering/lossless-claw project, so this fork is marked deprecated: new users are directed to install upstream directly, and it no longer compiles against current OpenClaw releases.

More in Agent memory

See all 450

  • AI Agent Memory: The Definitive Guide

    cognee.ai

    A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • lossless-memory

    note.com

    A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy