DSH-PLUGIN STORE / LIVE CATALOG

DSH插件商店

聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。

已收录
6553
功能分类
11
更新时间
10/07 02:01

25 个项目,匹配「compaction」

Agent 与会话 插件

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

acp billion-context context-management dsh-plugin
Agent 与会话 索引目录

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.

agent agent-memory agent-middleware awesome-list
Agent 与会话 插件

LLM-free lossless* compaction engine for DeepSeek Harness

agent compaction context-compression cordis
Agent 与会话 插件

dsh-force-compact

falling-ts

Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。

context-compaction cordis deepseek deepseek-harness
Agent 与会话 插件

dsh-argp

yoza10635

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. 守卫式上下文压缩:LLM 只提议、确定性守卫裁决——逐原子缩放 + 惰性引用图剪枝(0-LLM)+ 追加式日志逐字节召回;压缩率精确兑现,历史永不销毁。

agent compaction context-compression cordis
Agent 与会话 插件

DeepSeek Harness 的上下文压缩插件

context-compaction deepseek-harness dsh-plugin memory
Agent 与会话 完整应用

taskfold

yindf

Context folding for DeepSeek Harness (DSH): wrap work in named tasks, fold finished spans into short summaries, recall originals on demand.

agent-memory ai-agents coding-agent compaction
Agent 与会话 插件

Codex-style context window auto-management for DeepSeek Harness — lossless zero-model context rollover

compaction context-management context-window dsh-plugin
Agent 与会话 插件

Context Assembler DSH — DeepSeek Harness 上下文汇编插件:按话题块编排上下文,最大化每 token 互信息密度

context-assembly context-compaction context-compression deepseek-harness
Agent 与会话 插件

dsh-context-zip

brunhildzhou

DSH 插件:接管 DeepSeek Harness 的会话压缩,产出结构化交接摘要、可回查分段与检索工具|A DSH plugin that takes over session compaction.

ai-agent compaction context-compression context-management
Agent 与会话 插件

dsh-agent-compact

MimicHunterZ

DSH plugin for agent-driven span compaction: compress chosen conversation spans into self-written checkpoints instead of the official head-anchored full-context sweep.

context-compression deepseek-harness dsh-plugin
Agent 与会话 插件

Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.

compaction context-management cordis deepseek-harness
Agent 与会话 插件

dsh-jev-prune

yangyu666

Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

agent context-compaction cordis deepseek-harness
Agent 与会话 插件

Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness.

context-compaction cordis deepseek-harness dsh
Agent 与会话 插件

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable notes, verbatim recent tail, no summarization

ai-agent compaction context-management context-window
Agent 与会话 插件

dsh-epistemic-fold

orangeofcarl0-sys

A contract-preserving context runtime for long-horizon agents on DeepSeek Harness

agent-memory context-compaction deepseek-harness dsh-plugin
Agent 与会话 插件

Session handoff & context management for DeepSeek Harness: structured handoff docs (export/resume/status) + active context pruning (acp_* via official compaction API) + optional OpenViking/archify enhancers

compaction context deepseek-harness dsh
Agent 与会话 技能

dsh-task-stack

Ray1270

Persistent per-session task stack for DeepSeek Harness agents - focus_task / focus_complete / read_focus + /focus, zero prompt injection

agent-skills context-compaction cordis deepseek-harness
Agent 与会话 插件

dsh-context-truth

deepseekv41flash

给 DSH 模型每轮回填宿主实测的上下文占用,并阻止"上下文快用尽"的错判被压缩摘要继承。

ai-agents compaction context-window deepseek-harness
Agent 与会话 插件

为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩,解决极简模式长任务无法持续工作的问题。

auto-compaction context-compaction context-window deepseek-harness
Agent 与会话 插件

Bridge DeepSeek Harness (DSH) session compaction summaries into Hermes Agent persistent memory. 把 DSH 会话压缩总结自动桥接进 Hermes 永久记忆。

ai-agents cordis deepseek-harness dsh
Agent 与会话 插件

Windowed, reversible context management for DeepSeek Harness (DSH): compression, historical retrieval, and native compaction integration.

acp ai-agent context-compression context-management
Agent 与会话 插件

dsh-clear-mind

john-walks-slow

Context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.

ai-agent context-compaction deepseek-harness dsh-plugin
Agent 与会话 插件

dsh-handoff-compaction

knighthongyu

Context compression for DSH: visually configure summary and recent-context budgets (8k + 16k by default), keep tasks on track, and search full conversation history. Friendly to small-context models.

context-compaction deepseek-harness dsh-plugin