Bundle
dsh-compaction-instant
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
TsFreddie14
Browse
8 results
Bundle
@mimichunterz/agent-compact
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
MimicHunterZ4
Bundle
dsh-context-management
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
PlxloYzb1
Bundle
dsh-squeeze-command
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
hardes111
Bundle
dsh-compressor
In-process DeepSeek Harness context compression bundle
Bundle
@jxame/dsh-condense
Token optimizer for DeepSeek Harness — condense your context, keep the essence
JxaMe
Bundle
@dsh-external/dsh-context-economy
Token-efficient project reading with symbol/import indexing, PageRank topology, and byte-level slicing for DSH
huangjua
Bundle
billion-context-dsh
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
Tyan66666