DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Community Feature Requests — Plugin Hub News
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

COMMUNITY CHALLENGES

Find your next challenge.

Real problems from the community. Find one that sparks an idea, explore the discussion, and build something people need.

Showing 61–80 of 95 community requestsUpdated hourly from community discussions
All updatesDSH ReleasesFeature Requests
All3 days7 days14 days
TopNew
OpenShippedSolved by pluginWon't fixAll statuses

Window Sep 13, 2026 – Sep 20, 2026

#Problems worth solvingCommunity demand
61▼17
HARNESS
4hackernews5

Configure models and reasoning per teammate

Allow team leads or agent-teams users to independently select a provider, model, and reasoning effort for each teammate, including cheaper or local models.

Explore challenge ↗

The problem

Allow team leads or agent-teams users to independently select a provider, model, and reasoning effort for each teammate, including cheaper or local models.

Possibly addressed by:Agent Team Model · Agent Teams · Agent Teams

Start with these discussions

  • tool-agent-team：agent/created 时序竞态会随机杀死一次性子代理（TEAM_NOT_MEMBER）github · ▲1 · 2 comments
  • Model selection in agent-teamsgithub · ▲1 · 0 comments
  • 【功能建议】Agent Team模式建议加入可以让Lead给teammate指定模型的功能github · ▲1 · 0 comments
Last active Sep 17, 2026
1 authors1 posts · 1 reactions0 comments
62▼17
HARNESS
2

Add lazy loading for session lists

Make workspace session lists load lazily or incrementally so large lists remain usable over slow or tunneled network connections and avoid timeouts.

Explore challenge ↗

The problem

Make workspace session lists load lazily or incrementally so large lists remain usable over slow or tunneled network connections and avoid timeouts.

Possibly addressed by:More Session Operations · Session Usage · Session Xc

Start with these discussions

  • 远程打开dsh web页面,无法打开session 列表github · ▲1 · 1 comments
  • [bug] `@deepseek-ai/dsh-api-session-controller` 的 `session/list` 默认全量加载，随使用数据逐渐爆炸，建议增加分页、懒加载机制github · ▲1 · 0 comments
Last active Sep 17, 2026
1 authors1 posts · 1 reactions0 comments
63▼4
HARNESS
2

Add a new-conversation composer dock

Expose an additive, extensible UI slot immediately below the zero-turn new-conversation composer, preserving normal document flow, registration order, and session-specific visibility without replacing the resident input.

Explore challenge ↗

The problem

Expose an additive, extensible UI slot immediately below the zero-turn new-conversation composer, preserving normal document flow, registration order, and session-specific visibility without replacing the resident input.

Possibly addressed by:Conversation Flat · Client Ui Selection Add · Subagent Panel

Start with these discussions

  • 在新会话页的输入卡片下方，能否增加一个 slot？github · ▲1 · 0 comments
  • Hero Composer lacks an additive public dock below the zero-turn InputBargithub · ▲1 · 0 comments
Last active Sep 15, 2026
1 authors1 posts · 1 reactions
64▲4
HARNESS
2

Bound and resume session streaming

Optimize remote session delivery over slow or unreliable WebSocket connections by bounding or chunking snapshots, compressing transfers, prioritizing heartbeats, and resuming incremental updates instead of retransmitting large windows.

Explore challenge ↗

The problem

Optimize remote session delivery over slow or unreliable WebSocket connections by bounding or chunking snapshots, compressing transfers, prioritizing heartbeats, and resuming incremental updates instead of retransmitting large windows.

Possibly addressed by:Session Snapshot · Session Handoff · Session Robustness

Start with these discussions

  • 性能优化提案：压缩 remote.mux WebSocket（permessage-deflate）并为首屏快照设界——移动端/远端链路实测首屏缩小 5~8 倍github · ▲1 · 0 comments
  • 关于WebSocket承载大体积数据的问题：慢链路下心跳误杀 + 整窗重发风暴github · ▲1 · 0 comments
Last active Sep 20, 2026
1
65
HARNESS
2

Make Settings Navigation Independently Scrollable

Add an independent vertical scroll area for the Settings dialog’s left navigation so all sections remain accessible in short or zoomed viewports. Keep the title fixed, preserve keyboard access, and prevent navigation scrolling from affecting the content pane.

Explore challenge ↗

The problem

Add an independent vertical scroll area for the Settings dialog’s left navigation so all sections remain accessible in short or zoomed viewports. Keep the title fixed, preserve keyboard access, and prevent navigation scrolling from affecting the content pane.

Possibly addressed by:Settings Nav Scroll · Settings Sections · Settings Nav Organizer

Start with these discussions

  • [Bug/Feature] 设置对话框左侧导航栏在分区较多时溢出被裁切：navList 不可滚动github · ▲1 · 0 comments
  • Settings: independently scroll the section sidebar / 设置左侧配置列表支持独立滚动github · ▲1 · 0 comments
Last active Sep 15, 2026
1 authors
66
HARNESS
1hackernews1

Reduce reasoning token usage

Optimize reasoning so models use fewer tokens, especially when verbose or overthinking during complex tasks.

Explore challenge ↗

The problem

Optimize reasoning so models use fewer tokens, especially when verbose or overthinking during complex tasks.

Possibly addressed by:Token Saver · Token Optimizer · Token Stats

Start with these discussions

  • 思考时输出大量内容是否加速token消耗github · ▲1 · 0 comments
  • Comment on: Hy4 previewhackernews · ▲0 · 0 comments
Last active Sep 15, 2026
1 authors1 posts · 1 reactions0 comments
67▼45
HARNESS
4

Support multi-session plugin work areas

Allow plugins to render multiple session views simultaneously in shell-managed, independently laid-out panes, with each view bound to its own session rather than the global selection.

Explore challenge ↗

The problem

Allow plugins to render multiple session views simultaneously in shell-managed, independently laid-out panes, with each view bound to its own session rather than the global selection.

Possibly addressed by:Split Panes · Plugin Archived Sessions · Side Session

Start with these discussions

  • 插件生态诉求：官方侧边会话渲染面 / 快照字段稳定性承诺 / 只读权限 presetgithub · ▲1 · 1 comments
  • 提案：为插件提供工作区域与唯一原生会话伴随栏github · ▲1 · 1 comments
  • Client: keep more than one session live at a time (multi-pane conversation rendering)github · ▲1 · 0 comments
68▼51
PLUGIN
11

Discover providers and models dynamically

Discover provider and model catalogs through live APIs, including third-party providers such as OpenRouter, and populate the settings UI with available models and metadata. Retain bundled, cached, or temporary override data as fallbacks when discovery is unavailable.

Explore challenge ↗

The problem

Discover provider and model catalogs through live APIs, including third-party providers such as OpenRouter, and populate the settings UI with available models and metadata. Retain bundled, cached, or temporary override data as fallbacks when discovery is unavailable.

Possibly addressed by:Model Catalog Refresh · Live Model Catalog · Catalog Refresh

Start with these discussions

  • Provider model catalogs are stale for OpenCode Go and OpenRoutergithub · ▲11 · 4 comments
  • 支持 OpenCode Go 的最新模型列表github · ▲6 · 1 comments
  • 针对第三方提供商配置体验优化的问题
69▼22
HARNESS
2

Support WebMCP Tool Discovery and Reuse

Enable DSH agents and browser plugins to discover and invoke WebMCP tools, then build, verify, version, manage, and reuse them across websites. This includes the core WebMCP support requested for using page-provided capabilities while reducing repeated interactions and token costs.

Explore challenge ↗

The problem

Enable DSH agents and browser plugins to discover and invoke WebMCP tools, then build, verify, version, manage, and reuse them across websites. This includes the core WebMCP support requested for using page-provided capabilities while reducing repeated interactions and token costs.

Possibly addressed by:Web Bridge Mcp · Mcphub · Mcp Manager

Start with these discussions

  • Support webMCPgithub · ▲3 · 3 comments
  • DeepSeek Harness + WebMCP + Builder = Efficient Computer Usegithub · ▲2 · 2 comments
Last active Sep 7, 2026
70▼44
HARNESS
2

Make the Plan View Persistent and Expandable

Keep the plan view available after selections and provide a collapsible, resizable, or expanded layout for comfortable repeated viewing. Preserve plan actions such as approving the plan and continuing to plan.

Explore challenge ↗

The problem

Keep the plan view available after selections and provide a collapsible, resizable, or expanded layout for comfortable repeated viewing. Preserve plan actions such as approving the plan and continuing to plan.

Possibly addressed by:Plan Plus · Plugin Better Plan · Plan Toggle

Start with these discussions

  • [功能建议] plan 模式的计划视图增加全屏 / 侧边栏查看能力github · ▲3 · 1 comments
  • 计划模式中的计划面板能否支持反复查看？github · ▲1 · 0 comments
Last active Sep 11, 2026
0 authors0 posts · 2 reactions1 comments
71
HARNESS
hackernews2

Increase Parallel Agent Capacity

Allow DSH to run a larger number of agents concurrently, increasing multi-agent capacity and throughput.

Explore challenge ↗

The problem

Allow DSH to run a larger number of agents concurrently, increasing multi-agent capacity and throughput.

Possibly addressed by:Subagent Concurrency Limit · Parallel Agent Ade · Background Agents

Start with these discussions

  • Comment on: DeepSeek v4.1 Flash Is Now Our Best Hacking Modelhackernews · ▲0 · 0 comments
  • Comment on: Claude Fable 5.1 and Claude Mythos 5.1hackernews · ▲0 · 0 comments
Last active Sep 16, 2026
1 authors1 posts · 0 reactions0 comments
72
HARNESS
1hackernews1

Support Android and Termux

Enable official installation and execution of DSH on Android, including Termux, with the required portability, filesystem, runtime, and installation handling.

Explore challenge ↗

The problem

Enable official installation and execution of DSH on Android, including Termux, with the required portability, filesystem, runtime, and installation handling.

Possibly addressed by:Android Agent · Android · Plugin Android Use

Start with these discussions

  • dsh runs on Termux (Android) — with 5 small patchesgithub · ▲9 · 0 comments
  • Comment on: Ask HN: What are you working on? (September 2026)hackernews · ▲0 · 0 comments
Last active Sep 14, 2026
1 authors1 posts · 0 reactions0 comments
73
HARNESS
hackernews3

Coordinate parallel coding-agent teams

Provide orchestration for multiple coding-agent teams or workers running in parallel, with shared relevant context, coordination, and ongoing feedback between them.

Explore challenge ↗

The problem

Provide orchestration for multiple coding-agent teams or workers running in parallel, with shared relevant context, coordination, and ongoing feedback between them.

Possibly addressed by:Subagent Profile · Background Agents · Parallel Agent Ade

Start with these discussions

  • Comment on: Show HN: Share your AI Setup, Learn from othershackernews · ▲0 · 0 comments
  • Comment on: GLM-5.3-Flashhackernews · ▲0 · 0 comments
  • Comment on: DeepSeek V4 Flash 0731hackernews · ▲0 · 0 comments
Last active Sep 17, 2026
1 authors1 posts · 0 reactions0 comments
74▲1
HARNESS
1hackernews71

Preserve Unified Sessions Across Providers and Handoffs

Preserve complete conversation, memory, tools, prompts, workspace, and unfinished-work state when switching channels, agents, models, or workflows. Use provider-independent transcripts and centralized project configuration so sessions can move without manual copying or silent rebuilding.

Explore challenge ↗

The problem

Preserve complete conversation, memory, tools, prompts, workspace, and unfinished-work state when switching channels, agents, models, or workflows. Use provider-independent transcripts and centralized project configuration so sessions can move without manual copying or silent rebuilding.

Possibly addressed by:Background Agents · Agent Mode Switcher · Subagent Model Picker

75▲3
HARNESS
2

Support Local Models

Allow DeepSeek Harness to add and run locally hosted models such as Qwen, reducing reliance on remote services and accommodating lower-resource setups.

Explore challenge ↗

The problem

Allow DeepSeek Harness to add and run locally hosted models such as Qwen, reducing reliance on remote services and accommodating lower-resource setups.

Possibly addressed by:Local Ai · Plugin Local Model · Local Llm

Start with these discussions

  • there should be a option of adding local models to deepseek harness ......the whole ai world will change once in for allx · ▲0 · 0 comments
  • @Taniyatweets_ I want to run a local model and local harness. Something like qwen model and deepseek harness. 32GB is nox · ▲0 · 0 comments
Last active Sep 16, 2026
1 authors1 posts · 0 reactions0 comments
76▼26
HARNESS
hackernews3

Provide reusable on-demand skills for custom workflows

Let users package custom agent flows as reusable skills and define repeatable, on-demand tasks outside AGENTS.md. This enables workflows such as migrations or component generation without unnecessarily polluting the agent’s context.

Explore challenge ↗

The problem

Let users package custom agent flows as reusable skills and define repeatable, on-demand tasks outside AGENTS.md. This enables workflows such as migrations or component generation without unnecessarily polluting the agent’s context.

Possibly addressed by:Agent Useful Skills · Skill Creator · Agent Skills

Start with these discussions

  • Comment on: Claude Code now reads AGENTS.md if there is no Claude.mdhackernews · ▲0 · 0 comments
  • Comment on: OpenAI Agents APIhackernews · ▲0 · 0 comments
  • Comment on: Ask HN: How do you manage skills files?hackernews · ▲0 · 0 comments
Last active Sep 18, 2026
1 authors1 posts · 0 reactions0 comments
77▲2
HARNESS
hackernews11

Cache and reuse prompt-processing slots

Add native prompt/prefix caching that saves prompt-processing slots, optionally in a RAM disk, and reuses them across forked conversations, chat windows, subagents, and parallel requests to avoid duplicate prefill work and reduce latency.

Explore challenge ↗

The problem

Add native prompt/prefix caching that saves prompt-processing slots, optionally in a RAM disk, and reuses them across forked conversations, chat windows, subagents, and parallel requests to avoid duplicate prefill work and reduce latency.

Possibly addressed by:Granular Prompt · Prompt Injector · Prompt Stash

Start with these discussions

  • Prompt processing takes 21 seconds, so reading it from a RAMDISK should reduce it to 1-2 secondsx · ▲0 · 0 comments
  • Comment on: Speculative Decoding in vLLM on AMD GPUshackernews · ▲0 · 0 comments
Last active Sep 18, 2026
1 authors1 posts · 0 reactions0 comments
78
HARNESS
hackernews2

Support metric units

Provide metric-unit support throughout the harness, including meters for measurement and monitoring capabilities.

Explore challenge ↗

The problem

Provide metric-unit support throughout the harness, including meters for measurement and monitoring capabilities.

Possibly addressed by:Usage Meter Harness · Units · Meter

Start with these discussions

  • Comment on: Ask HN: What are you working on? (September 2026)hackernews · ▲0 · 0 comments
  • Comment on: Ask HN: What are you working on? (August 2026)hackernews · ▲0 · 0 comments
Last active Sep 14, 2026
1 authors1 posts · 0 reactions0 comments
79▼45
HUB
hackernews4

Create a unified skills registry and standard

Provide a centralized, standardized registry for creating, discovering, versioning, distributing, and synchronizing reusable agent skills across compatible agents and developers.

Explore challenge ↗

The problem

Provide a centralized, standardized registry for creating, discovering, versioning, distributing, and synchronizing reusable agent skills across compatible agents and developers.

Possibly addressed by:Skills Hub · Skill Manage · Skills Anywhere

Start with these discussions

  • Comment on: Claude Code now reads AGENTS.md if there is no Claude.mdhackernews · ▲0 · 0 comments
  • Comment on: Ask HN: How do you manage skills files?hackernews · ▲0 · 0 comments
  • Comment on: Ask HN: How do you manage skills files?hackernews · ▲0 · 0 comments
Last active Sep 18, 2026
1 authors1 posts · 0 reactions0 comments
80▲5
HARNESS
1hackernews1

Centralize session-scoped tool permissions

Add a centralized authorization and sandbox-control layer that enforces per-user or per-session isolation across filesystem, shell, and other tool operations without requiring each tool to be modified. It should support users owning the underlying compute while keeping access boundaries centrally enforceable.

Explore challenge ↗

The problem

Add a centralized authorization and sandbox-control layer that enforces per-user or per-session isolation across filesystem, shell, and other tool operations without requiring each tool to be modified. It should support users owning the underlying compute while keeping access boundaries centrally enforceable.

Possibly addressed by:Strip Sandbox Permissions · Session Allow · Auto Approval Plugin

Start with these discussions

  • 做权限隔离需要改动很多工具代码github · ▲1 · 1 comments
  • Comment on: Show HN: Share your AI Setup, Learn from others
← PreviousPage 4 of 5Next →
0 comments
authors
1 posts · 1 reactions
0 comments
1 posts · 1 reactions
0 comments
Last active Sep 14, 2026
1 authors1 posts · 1 reactions0 comments
github · ▲2 · 1 comments
Last active Sep 12, 2026
0 authors0 posts · 4 reactions1 comments
0 authors
0 posts · 2 reactions
2 comments

Start with these discussions

  • 子代理加了创建时选模型后，运行中反而切不了了github · ▲1 · 0 comments
  • Comment on: HarnessTax: How Much Does the Harness Matter for Coding Agents?hackernews · ▲0 · 0 comments
  • Comment on: OpenAI Agents APIhackernews · ▲0 · 0 comments
Last active Sep 18, 2026
1 authors1 posts · 0 reactions0 comments
hackernews · ▲0 · 0 comments
Last active Sep 17, 2026
1 authors1 posts · 0 reactions0 comments