LLM-free lossless compression engine
KitDoesIt/dsh-compaction-instant · skills
LLM-free lossless compaction engine for DeepSeek Harness.
★ 7GitHub stars
0Forks
2026-08-14Last updated
JavaScriptLanguage
MITLicense
Key features
- LLM-free — compaction never invokes a model.
- Instant — the compile is a single deterministic pass over the shadowed nodes
- Tool results cost nothing — results never produce entries
- No summarizer call → compaction latency goes from seconds to milliseconds
- No summarizer prompt, no inference latency, no token spend
Install command
dsh plugin --profile web add github:KitDoesIt/dsh-compaction-instant