dsh-model-switch
lincong1987
dsh plugin: flexible model switch for sub‑agent & plan execution. 为子代理和计划执行选择更合适的模型。
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
126 个项目,匹配「x」
lincong1987
dsh plugin: flexible model switch for sub‑agent & plan execution. 为子代理和计划执行选择更合适的模型。
lynx-gt
DeepSeek Harness subagent delegation enhancement
polaris-smart
Turn your devices into a fleet — dph plugin for decentralized multi-device collaboration: mDNS discovery, key pairing, SSH direct exec. Tools auto-register for dph agents.
wjabanjj
AiFP 记忆感知系统|MCP 服务,一套记忆全 AI 共享。面向中文的 Agent 感知记忆,支持叙事链、语义纠错、感知链图扩散。兼容 DeepSeek‑Harness、Claude Code、Cursor、Codex等全部 MCP 客户端,数据完全本地存储。
wxxb789
DeepSeek Harness (DSH) plugin for multi-agent orchestration: semantic agent Profiles, exact LLM model routing, declarative Teams and Strategies, and bounded subagent delegation in TypeScript.
x118111
A DeepSeek Harness (DSH) dynamic plugin that adds an ✨ optimize-prompt button to the chat composer — context-aware LLM rewriting with model fallback and visible errors.
Chillizu
DeepSeek Harness 插件集——恢复/执行/授权/探测/学习/遥测 7 个单职责插件 + miopiik preset 模板 | Single-purpose plugin suite for DeepSeek Harness (DSH): checkpoint/rewind recovery, scoped executor subagents, model authorization gate, capability probing, skill minting, token telemetry — plus the miopiik 4-layer workflow preset template
JD962
This plugin was developed using DeepSeek Harness and the DeepSeek V4 Flash 0731 / Pro 0813 models, with multiple rounds of refinement. It enhances the existing sub‑agent functionality and adds several other features.
JunNanLYS
让 DeepSeek Harness 拥有长期记忆:对话自动蒸馏为事实/场景/画像三层记忆,每步自动召回注入——让 AI 基于证据说话,零操作无感使用 | Long-term memory for DeepSeek Harness: conversations auto-distilled into facts, scenes & persona, recalled before every step — so the AI speaks from evidence, not guesses. Zero effort.
KaichenCurry
TabNexus for DSH:零 Chrome 依赖的浏览器任务上下文插件(dsh-plugin 生态)。任务文档、AI 整理、全局工作区,装完即用。
LeslieWylie
A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.
Max-Null
该仓库暂未提供项目说明。
NelsonLongxiang
Quick prompt templates for DeepSeek Harness: global and per-session templates, a right-side panel, and Python-backed SQLite persistence
afa-cloud
Cross-platform macOS desktop GUI automation & computer-use skill built on cua-driver: AX→pixel→desktop graceful degradation, vision-based element locating, privacy(automation) handling, and ready-made recipes for WeChat / iPhone Mirroring / QQ.
chiro2001
DeepSeek Harness 动态上下文管理插件(Dynamic Context Pruning for dsh),对标 opencode-dcp
february2015
TaskSwarm (蜂群) — DeepSeek Harness 上的多智能体任务编排插件:waves/lanes 并行执行、git worktree 隔离、任务包与跨模型评审、崩溃可恢复 | Multi-agent task orchestration for DeepSeek Harness: waves/lanes parallel execution, git worktree isolation, task packets, cross-model review, crash recovery
green-dalii
Two-tier model router for DeepSeek Harness — LLM-Judge routing, multi-model fallback chains, exponential-backoff failover, and task-level orchestration (DSH adaptation of pi-shift-router)
helloxkk
Context visibility + GitHub-style usage heatmap for DeepSeek Harness (dsh) — Codex-style /context lens + 53-week contribution graph
jinhuang712
Link and read DSH sessions: one-click @session-id reference, an @ mention menu by title, and a session_read tool that projects any session to readable text. DeepSeek Harness plugin.
lifeodyssey
DeepSeek Harness plugin: compress tool output, cut up to 20% of context, without touching the context cache or agent performance.
lmst2
该仓库暂未提供项目说明。
memorax-ai
Agent knowledge hub and deepseek-harness plugin
peterwangze
AI coding delivery trust layer for evidence-backed planning, review, risk, quality, and release control.
r600a-code
DSH plugin: sub-agent matrix swarm — routes heterogeneous tasks to the most suitable model (OpenRouter-like + cfgpu.com/llm/square), dispatches each via in-process subagents. 32/32 benchmark green.