by win4r · Codex Skill · ★ 546
🦞lossless-claw-enhanced Enhanced fork of Martian-Engineering/lossless-claw — fixes CJK token estimation and cherry-picks critical upstream bug fixes for production reliability. Lossless Context Management plugin for OpenClaw, based on the LCM paper from 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. Video Tutorial Full walkthrough: installation, configuration, and hybrid retrieval internals.
| Stars | 546 |
| Forks | 108 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 59.024/100 |
| Open Issues | 2 |
| Last Updated | 2026-05-21 |
| Created | 2026-03-28 |
| Platforms | node |
| Est. Tokens | ~763k |
These tools work well together with lossless-claw-enhanced for enhanced workflows:
Explore other popular codex skill tools:
lossless-claw-enhanced is Fork of Martian-Engineering/lossless-claw with CJK-aware token estimation. It is categorized as a Codex Skill with 546 GitHub stars.
lossless-claw-enhanced is primarily written in TypeScript. It covers topics such as openclaw, openclaw-plugin, openclaw-skills.
You can find installation instructions and usage details in the lossless-claw-enhanced GitHub repository at github.com/win4r/lossless-claw-enhanced. The project has 546 stars and 108 forks, indicating an active community.
lossless-claw-enhanced is released under the MIT license, making it free to use and modify according to the license terms.