Cordis

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。

Awesome Claude Mods — evidence-graded index of Claude Code mods, plugins and hooks. 20 languages, rebuilt every 2 hours.

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）。

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

双击一个文件，给 DeepSeek Harness 加一个「破甲模式」Agent Preset —— 零侵入、零依赖、双击无黑框，不改 DSH 一字节代码，升级不丢。

DeepSeek Harness (dsh) Windows desktop client - bundled Node.js + dsh CLI, one-click launch

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

Composable mathematics tools for agents

面向 AI Coding Agent 的任务感知工作区上下文检索与生命周期追踪：按当前任务找到、组织并持续追踪最相关的文档、代码与媒体。纯本地、零模型调用、零网络。 Task-aware workspace context retrieval and lifecycle tracking for AI coding agents. Find, organize, and track the workspace context most relevant to the task at hand — locally, deterministically, zero model calls, zero network.

一套 DSH runtime，Desktop、Web 与 TUI 三种开发体验。

DSH最稳定，最高效的破甲插件：token 级重试环 + 三层技能路由（形态/父/叶）+ 分级 prefill + 拒答阶梯自我强化 L0–L3 + finish_reason 四路分流 + 请求体级整形

Open Reality: phone video to AI-queryable 3D scenes. MCP tools for Claude/Codex/Cursor (npm openreality-mcp), the self-hostable broker, and the VGGT-SLAM library, in one repo. BSD-2-Clause.

Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracking, company research cards, and auditable research reports. Research only - not investment advice.

FROZEN 2026-10-05 — Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

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

让 AI 与人类一起攻克真正的科学难题 —— 12 阶段 55 门 · 36 工具 · 98 条技能 · 证据链与可复现

DeepSeek Harness 桌宠：元气鲸鱼娘，45 项成就、3 个小游戏、跨端存档迁移；按工具类型切换工作姿态，桌面端与旧版 Web 双端支持（desktop pet / mascot，local-first）

A curated list of plugins for DeepSeek Harness (dsh) - DeepSeek Harness plugin ecosystem

从零开始，看懂 DeepSeek Harness 的「万物皆可插件」— 零基础插件开发教程（含 22 个中文技能实例）| Zero-to-plugin tutorial for DeepSeek Harness

Time-shifting task delegation for DeepSeek Harness (dsh): plan tasks at leisure, they run unattended off-peak, come back to a report. Human-adjudicated, desktop + web.

把本机 WorkBuddy 桌面端已登录的模型（DeepSeek / GLM / Kimi / MiniMax 等）变成本地的 OpenAI 与 Anthropic 兼容接口 —— Claude Code / opencode / Cursor / Trae / Cherry Studio / LobeChat 等任意支持自定义 Base URL 的客户端可直连。附网页控制台与 DeepSeek Harness 原生插件。零依赖，仅监听 127.0.0.1。

ACRYL - Agent Context Relay Yielding Lifecycles. One persistent workspace, one canonical context, any coding agent.

DeepSeek Harness (DSH) Python 教程：17 章从零实现 Agent Loop、插件系统、工具调用、Session、上下文工程、Subagent 与 Headless CLI