The "context-compression" topic on GitHub groups 10 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-argp with 9 GitHub stars. dsh-argp — Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness auxiliary model plugin: provides independent model routes, tools and system prompts for vision understanding, context compression, approval review, sub-agents, session titles and image generation, never touching the main conversation model.
DSH plugin for agent-driven span compaction: compress chosen conversation spans into self-written checkpoints instead of the official head-anchored full-context sweep.
