Compresses workspace memory and transcripts to reduce token costs.
npx skills add https://github.com/aeromomo/claw-compactor --skill claw-compactor
Please help me install this Agent Skill. Skill: claw-compactor Source: https://github.com/aeromomo/claw-compactor/tree/main Command: npx skills add https://github.com/aeromomo/claw-compactor --skill claw-compactor
Claw Compactor reduces token usage by compressing memory and transcripts using five layered techniques, enabling faster AI workflows.
Point this AI at a workspace and run the full pipeline to compress memory and transcripts.
High-intent search queries and answers about installing and using this skill.
To compress markdown memory files and reduce token usage, this skill applies a 5-layer pipeline that generates tiered MEMORY.md summaries and a dictionary codebook for efficient context loading. It enforces deterministic, auditable transformations.
The best way to compress session transcripts is using selective lossy compression that preserves decisions and actions. This skill reduces transcript tokens by applying dictionary encoding and observation-based summaries alongside memory compression.
Yes, the memory compression pipeline requires the tiktoken dependency to process markdown memory files and transcripts. It uses this to generate tiered L0/L1/L2 summaries and a codebook for efficient context loading.
You can audit and reverse compression steps because the pipeline enforces deterministic, auditable transformations with reversible compression. It provides on-demand scripts and references for troubleshooting, auditing, and extending the pipeline.
You generate tiered MEMORY.md summaries and a dictionary codebook by pointing the AI at a workspace and running the full compression pipeline. It automatically creates L0/L1/L2 summaries for efficient context loading.
itsmarsssIngest OpenClaw workspace memory and session transcripts into an Obsidian wiki.
c-dalySave user learnings to persistent .context/MEMORY.md files with optional scope.
georgekhananaevCompress Markdown and text into token-efficient formats with Python scripts.
oimiragieoCondense long documents, code, and conversations into concise summaries.
