billion-context-dsh

DeepSeek Harness Memory Low risk

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

模型驱动的上下文压缩（Active Context Pruning）：由模型决定何时压缩、压缩什么。

How to install

DeepSeek Harness dsh plugin add billion-context-dsh

About

billion-context-dsh 中文 | English **⚠️ 测试版声明——请勿用于生产环境** 本项目（**v0.2.2**）仍处于开发中的测试版。DeepSeek Harness 本身也处于**公开测试版**阶段。**请勿将两者用于工程化 / 生产环境**——预期会有破坏性变更与粗糙之处。由模型决定<em>何时</em>压缩、<em>压缩什么</em>——而不是一个硬性上限。 --- --- 为什么？当对话变长，模型会耗尽上下文。多数工具直接硬截断——悄悄丢弃早期消息。**billion-context-dsh** 给模型一个 compress 工具：由 LLM 决定**何时**、**压缩什么**，写成高保真摘要，保留关键细节（文件路径、决策、错误信息）的同时回收上下文空间。与 DSH 内置的自动压缩（用自动生成的摘要替换一段范围）不同，billion-context-dsh： **模型驱动** —— 摘要由模型自己书写，没有第二次 LLM 摘要调用（ACP 的成本优势） **只建议、不强令** —— 自动策略只 *nudge*（提醒），是否压缩、何时压缩由模型决定 **持久且可恢复** —— 压缩范围成为 checkpoint 节点，原文保留在 append-only 会话日志中；decompress 可恢复，search_context 可在块内查找 *…

GitHub ↗

Recommendation signals

63 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

63 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings: None
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
Topics: acp, billion-context, context-management, dsh-plugin

Related plugins

DeepSeek Harness

Score98

hindsight

vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

☆ 27.7K ↓ 124.6K Memory ↗

MCP ServerClaude Code

Score91

firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

☆ 7.5K ↓ 126.7K Memory ↗

DeepSeek Harness

Score84

dsh-mnemon

omdsh-dev/dsh-mnemon

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

☆ 409 ↓ 36.1K Memory ↗

Claude Code

Score82

get-shit-done

gsd-build/get-shit-done

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

☆ 64.5K ↓ 48.4K Memory ↗