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。
让 DeepSeek Harness 人人可用的桌面入口——不用 Node、不用命令行,双击即用,还无损跟随每次官方更新。支持MacOs和Windows。DeepSeek Harness, for everyone. No Node.js. No command line. Just double-click and go. Always in step with every official update. For macOS & Windows.
A Command Code LLM provider plugin for DeepSeek Harness (dsh) — supporting all subscription plans (incl. Go & Pro) via Studio API / gateway.专为 DeepSeek Harness (dsh) 打造的 Command Code LLM 接入插件,全面支持包括 Go/Pro 在内的各类订阅方案。
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.
DeepSeek Harness (dsh) browser companion: Chrome side panel embedding the full dsh web UI + host plugins for page reading, HTTP capture, and browser control.
Self-evolve memory plugin for DeepSeek Harness: learns from your own sessions, injects token-budgeted preference summaries into every step. /memory commands, memory tool, settings panel. Local-only data.
为DSH接入本地大模型能力:在「设置→插件」页一键启停本地 llama.cpp 大模型(双槽x双模态x双预设),卡片内配置、一条命令安装、自动注册,装完即用| Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to use
Web-chat style message actions for DeepSeek Harness: edit your prompt, regenerate answers, and flip versions with a deepseek.com-style <i/N> pager. Deepseek网页版/app聊天体验插件