dsh-token-optimizer
Zoria-Lind
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
GITHUB TOPIC
7个项目包含此标签
7 个项目
GitHub Topic 精确匹配
Zoria-Lind
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
yindf
Context folding for DeepSeek Harness (DSH): wrap work in named tasks, fold finished spans into short summaries, recall originals on demand.
Snow-ea
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness.
Dreverie
Cut the input-token cost of long DeepSeek Harness sessions: source-side tool-output compression on tools/post-execute plus per-agent tool-catalogue visibility, with a measurement script.
LuminariSoftwares
Too many MCP servers eating your context? tool-guardian sits in front of all of them and loads each tool’s schema only when needed. A 7-server setup went from 20,005 tokens to 1,084. Any MCP client.
sutanglime
Companion-AI hot/cold memory for DeepSeek Harness: auto dialogue archive, graduated cooling, cue-gated recall, 1600-token memory snapshot. | 陪伴 AI 冷热分层记忆:全自动归档 + 渐进冷存 + 线索召回。
xiamubumu
DSH 1.5 上下文治理:折叠工具结果、保持提示词缓存命中、接管宿主可写请求(不再需要 dsh-llm 文件补丁)。仅支持 DSH 1.5,后续会跟进更新。 / Context governance for DSH 1.5: folds tool results, keeps the prompt cache warm, takes over the writable-request path. DSH 1.5 only; newer releases will follow.