dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor and any MCP client, with an immutable audit log and a token ledger. Open source, self-hosted, no cloud.

One-click prompt enhancement beside the DeepSeek Harness composer: rewrites a draft in place without sending it.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

官方 DeepSeek Harness 的交互式终端 UI 插件：自研 ANSI 极简交互渲染、流式 Markdown/工具卡、16+ 主题、slash 命令与选择器、输入历史与本地偏好持久化、LSP 诊断、memory记忆，很丝滑的开发体验。

💡DSH 的 Prompt提示词工具箱：常用prompt保存后点击即可注入到对话框——省时省力，/prompt 自动提示已有Prompt。 💡The Prompt toolbox for DSH: save frequently-used prompts and inject them into the dialog with one click — saving time and effort, with /prompt auto-suggesting your existing prompts.

DSH 破甲插件：token 级重试环 + 十片按需叶子（含邻近交付）+ 分级 prefill + 拒答阶梯 L0–L3 + finish_reason 四路分流 + 请求体级整形。零宿主补丁，188 项测试 / 56 条探针。

AI skills大全 mcp ai知识库 Agent 全维度 AI 资源百科，DSH插件 收录大模型、智能 Agent、RAG 检索增强、多模态、MLOps、AI 应用工具、AI面试集、Vibe coding 大全、零基础学习路线，持续更新前沿 AI 开源项目，开发者一站式 AI 导航库

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill toggles, zero tools, zero-cache-miss | DeepSeek Harness 插件：DietrichGebert/ponytail 懒人 senior 模式与七阶梯子完美移植，6 个技能描述双语自由切换

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

Reverse engineer anything with agents, from app behavior down to native binaries.

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Session preservation.

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

A reliable coding agent for complex software engineering tasks.