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 41–60 of 164 community requestsUpdated hourly from community discussions
All updatesDSH ReleasesFeature Requests
All3 days7 days14 days
TopNew
OpenShippedSolved by pluginWon't fixAll statuses
#Problems worth solvingCommunity demand
41
HARNESS
2

Detect stalled and idle Goal-mode continuation

Make Goal mode detect repeated no-progress rounds and waiting or idle states, pausing or stopping continuation when background work is running or no meaningful task remains. This prevents unnecessary calls, injected turns, and token consumption.

Explore challenge ↗

The problem

Make Goal mode detect repeated no-progress rounds and waiting or idle states, pausing or stopping continuation when background work is running or no meaningful task remains. This prevents unnecessary calls, injected turns, and token consumption.

Possibly addressed by:Goal Auto · Goal Pause Guard · Goal Restart

Start with these discussions

  • Goal模式空转，亟需优化github · ▲2 · 1 comments
  • goal 续行缺少"无进展"与"等待中"判断：0.1.6-alpha.2 仍复现github · ▲1 · 3 comments
Last active Sep 19, 2026
2 authors2 posts · 3 reactions4 comments
42
HARNESS
12

Add Desktop and TUI Interfaces

Provide official desktop and terminal user interfaces for DeepSeek Harness on Windows, macOS, and Linux, alongside the existing web interface, so users can access DSH through native or terminal surfaces.

Explore challenge ↗

The problem

Provide official desktop and terminal user interfaces for DeepSeek Harness on Windows, macOS, and Linux, alongside the existing web interface, so users can access DSH through native or terminal surfaces.

Possibly addressed by:Web Terminal · Tui · Omc Tui

Start with these discussions

  • [Feature Request] TUI支持github · ▲5 · 4 comments
  • @tianyi when are we getting the TUI for deepseek harness?x · ▲0 · 0 comments
  • Using official DeepSeek Harness (@deepseek-ai/dsh) and want a desktop or TUI surface?
43
HARNESS
3

Implement scoped, pluggable agent memory

Provide a backend-agnostic memory service or plugin with session, agent, and tenant isolation, automatic capture and recall, profile injection, safe lifecycle handling, and support for importing existing memories. Document secure multi-tenant integration and prevent races or duplicate writes during cleanup and migration.

Explore challenge ↗

The problem

Provide a backend-agnostic memory service or plugin with session, agent, and tenant isolation, automatic capture and recall, profile injection, safe lifecycle handling, and support for importing existing memories. Document secure multi-tenant integration and prevent races or duplicate writes during cleanup and migration.

Possibly addressed by:Plugin Memory · Agent Memory · Agentmemory

Start with these discussions

  • dsh-plugin: Native OpenViking memory for DeepSeek Harness (automatic session capture + memory tools + profile injection)github · ▲2 · 5 comments
  • 是否可以支持多租户记忆隔离，提供详细的api文档github · ▲1 · 3 comments
  • 给 #14 补点料：两个现成记忆实现里踩过的坑
44
PLUGIN
2

Map pi-ai reasoning tokens

Map the pi-ai provider’s reasoning-token count to `TokenUsage.reasoningTokens` while preserving output-token counts. Omit the field when the count is zero so reasoning and answer usage can be separated consistently across transcripts, context meters, and per-turn accounting.

Explore challenge ↗

The problem

Map the pi-ai provider’s reasoning-token count to `TokenUsage.reasoningTokens` while preserving output-token counts. Omit the field when the count is zero so reasoning and answer usage can be separated consistently across transcripts, context meters, and per-turn accounting.

Possibly addressed by:Plugin Reasoning Efforts · Thinking Token Stat · Custom Provider Reasoning

Start with these discussions

  • llm-pi-ai drops the reasoning-token breakdown pi-ai already reportsgithub · ▲2 · 2 comments
  • Map pi-ai's reasoning usage into `reasoningTokens`github · ▲1 · 2 comments
Last active Sep 18, 2026
45
HARNESS
2

Add Session Rewind and Code Rollback

Provide an official rewind capability that restores modified files and returns an agent session or experiment to a selected earlier timestamp or event, including truncating subsequent session history.

Explore challenge ↗

The problem

Provide an official rewind capability that restores modified files and returns an agent session or experiment to a selected earlier timestamp or event, including truncating subsequent session history.

Possibly addressed by:Session Rewind · Msg Rewind · Turn Rewind

Start with these discussions

  • 什么时候ds官方可以出一个rewind的功能呀github · ▲4 · 2 comments
  • Feature Request: 增加类似 Claude Code 的 /rewind 会话回退功能github · ▲2 · 0 comments
Last active Sep 15, 2026
2 authors2 posts · 6 reactions2 comments
46
HARNESS
1hackernews2

Provide a headless CLI

Provide a command-line, headless mode for DSH that exposes its capabilities through commands and arguments, enabling automated workflows, coordination of multiple harnesses, and use without VSCode.

Explore challenge ↗

The problem

Provide a command-line, headless mode for DSH that exposes its capabilities through commands and arguments, enabling automated workflows, coordination of multiple harnesses, and use without VSCode.

Possibly addressed by:Dcli · Skills Mcp Cli Manager · Cli

Start with these discussions

  • DSH应该支持CLIgithub · ▲2 · 4 comments
  • Comment on: Benzi – A harness reading LESS source code to write better quality codehackernews · ▲0 · 0 comments
  • Comment on: Ask HN: What are you working on? (August 2026)hackernews · ▲0 · 0 comments
47
PLUGIN
3

Add configurable developer-role compatibility

Make developer-role support configurable per model, defaulting to disabled for non-native OpenAI endpoints, and expose the setting in model configuration. This lets compatible providers opt in while preserving system roles for gateways that reject developer messages.

Explore challenge ↗

The problem

Make developer-role support configurable per model, defaulting to disabled for non-native OpenAI endpoints, and expose the setting in model configuration. This lets compatible providers opt in while preserving system roles for gateways that reject developer messages.

Possibly addressed by:Custom Provider Reasoning · Llm Openai Completions · Better Model Provider

Start with these discussions

  • [BUG] llm-pi-ai 应支持配置 compat.supportsDeveloperRolegithub · ▲11 · 5 comments
  • [bug or limits] bug 400: {"message":"Unexpected message role.","type":"BadRequestError","param":null,"code":400} while try reasoning with llm-pi-aigithub · ▲2 · 3 comments
  • 「续 #3379」建议：supportsDeveloperRole 默认改为 false，并在模型配置 UI 增加可见开关
48
HARNESS
2hackernews1

Relocate workspaces without losing history

Provide a supported, validated workflow to rename or move workspaces while preserving their identity, configuration, sessions, history, and related metadata.

Explore challenge ↗

The problem

Provide a supported, validated workflow to rename or move workspaces while preserving their identity, configuration, sessions, history, and related metadata.

Possibly addressed by:Workspace Mover · Session Workspace · Session Mover

Start with these discussions

  • Renaming a workspace folder makes its stored sessions fail the identity check, with no supported repairgithub · ▲1 · 1 comments
  • [Feature Request] Relocate a Project/Workspace folder without losing its sessions / 更换项目文件夹路径github · ▲1 · 0 comments
  • Comment on: Claude Code now reads AGENTS.md if there is no Claude.md
49
HARNESS
2

Enforce global subagent delegation budgets

Add hierarchical delegation limits, including effective concurrency caps, per-parent budgets, and whole-tree quotas, with clear rejection errors. Batch or consolidate settlement notifications and parent wakeups to prevent uncontrolled fan-out and repeated full-context runs.

Explore challenge ↗

The problem

Add hierarchical delegation limits, including effective concurrency caps, per-parent budgets, and whole-tree quotas, with clear rejection errors. Batch or consolidate settlement notifications and parent wakeups to prevent uncontrolled fan-out and repeated full-context runs.

Possibly addressed by:Subagent Concurrency Limit · Configurable Subagents · Subagent Profile

Start with these discussions

  • 子代理只有深度上限、没有广度/预算上限：一次会话产生 146 个子代理会话、3.43 亿缓存读取（占我全部历史 62%）github · ▲5 · 1 comments
  • subagent数量的上限无法有效设置github · ▲1 · 1 comments
Last active Sep 14, 2026
2 authors
50
HARNESS
2

Browse and view workspace files in the web UI

Add a web-based workspace browser that supports directory navigation, source-file viewing, and inspection of code changes. It should work well for remote or headless deployments and make agent edits accessible without a local editor.

Explore challenge ↗

The problem

Add a web-based workspace browser that supports directory navigation, source-file viewing, and inspection of code changes. It should work well for remote or headless deployments and make agent edits accessible without a local editor.

Possibly addressed by:Solution Explorer · Session Diff · Code Workbench

Start with these discussions

  • 可以提供类似opencode的web页面中源代码文件查看功能github · ▲1 · 4 comments
  • DSH的webUI看不到本地文件内容真的挺难受的github · ▲1 · 0 comments
Last active Sep 20, 2026
2 authors2 posts · 2 reactions4 comments
51
HARNESS
3

Add session-scoped filesystem workspaces

Give each session an isolated working directory and allow filesystem operations outside agent turns to target an explicit session scope. Propagate session identity through filesystem APIs and endpoints so shared DSH processes can safely serve multiple users.

Explore challenge ↗

The problem

Give each session an isolated working directory and allow filesystem operations outside agent turns to target an explicit session scope. Propagate session identity through filesystem APIs and endpoints so shared DSH processes can safely serve multiple users.

Possibly addressed by:Session Scope · Session Workspace · Multi Workspace

Start with these discussions

  • 同一个工作区内的会话为啥不做个目录隔离？github · ▲1 · 4 comments
  • Feature request: session scope for `fs`github · ▲1 · 0 comments
  • Session-scoped cwd: AgentLoop.create accepts one, the SDK wire has no way to send itgithub · ▲1 · 0 comments
52
HARNESS
5

Unify the Plugin Architecture

Build a minimal, flexible plugin-based core that supports user-created plugins across GUI and CLI environments, while implementing DSH’s own desktop capabilities as plugins.

Explore challenge ↗

The problem

Build a minimal, flexible plugin-based core that supports user-created plugins across GUI and CLI environments, while implementing DSH’s own desktop capabilities as plugins.

Possibly addressed by:Deepseek Harness Plugins · Plugin Optimization · Plugin Hub

Start with these discussions

  • @nachooolk @emanueledpt Also do you feel like it would be good if there was a plugin/customisation system so that you cax · ▲0 · 2 comments
  • @Teknium @honchodotdev @mem0ai Doesn't deepseek harness architecture serve as a better guide? If you look at it, you onx · ▲0 · 0 comments
  • I was thinking for hermes like deepseek harness concept. Means everything is plugin so hermes imo should able to createx · ▲0 · 0 comments
Last active Sep 19, 2026
5 authors5 posts · 0 reactions2 comments
53
HARNESS
hackernews7

Persist user instructions and preferences

Automatically load important instructions from persistent files and retain user preferences such as language and output style across conversations, long contexts, and sessions.

Explore challenge ↗

The problem

Automatically load important instructions from persistent files and retain user preferences such as language and output style across conversations, long contexts, and sessions.

Possibly addressed by:Agent Instructions As Prompt · Session Prompt · Prompt Polish

Start with these discussions

  • Comment on: Claude Code now reads AGENTS.md if there is no Claude.mdhackernews · ▲0 · 0 comments
  • Comment on: DeepSeek v4.1 Flashhackernews · ▲0 · 0 comments
  • Comment on: Claude Fable 5.1 and Claude Mythos 5.1hackernews · ▲0 · 0 comments
Last active Sep 18, 2026
7 authors7 posts · 0 reactions0 comments
54
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
2 authors2 posts · 9 reactions0 comments
55
PLUGIN
2

Allow Runtime Subagent Model Overrides

Expose runtime provider and model selection for subagent and subagent_fork tools, allowing users to inspect and switch running subagents independently while preserving parent-model inheritance by default.

Explore challenge ↗

The problem

Expose runtime provider and model selection for subagent and subagent_fork tools, allowing users to inspect and switch running subagents independently while preserving parent-model inheritance by default.

Possibly addressed by:Subagent Model Picker · Subagent Model · Submodel Change

Start with these discussions

  • [Bug] Subagent 工具未暴露 model/provider 参数，子代理强制继承父代理模型导致无法按需切换模型github · ▲1 · 3 comments
  • Clearly show the subagent model and let user change it on the flygithub · ▲1 · 1 comments
Last active Sep 18, 2026
2 authors2 posts · 2 reactions4 comments
56
HARNESS
3

Configure the composer send shortcut

Add a persisted composer preference that lets users choose whether Enter or Cmd/Ctrl+Enter sends a message, with the other action inserting a newline. Preserve IME composition, default behavior, and Queue/Steer semantics during execution.

Explore challenge ↗

The problem

Add a persisted composer preference that lets users choose whether Enter or Cmd/Ctrl+Enter sends a message, with the other action inserting a newline. Preserve IME composition, default behavior, and Queue/Steer semantics during execution.

Possibly addressed by:Enter Send · Ctrl Enter Submit · Queue First Enter

Start with these discussions

  • [Feature Proposal] Configurable idle Enter behavior: Enter = Send or Newline (Cmd/Ctrl+Enter to send)github · ▲1 · 3 comments
  • [Feature Request] Configurable composer send shortcut: Ctrl/Cmd+Enter to send, Enter inserts a newlinegithub · ▲1 · 0 comments
  • Feature request: optional "Enter key behavior" - Enter inserts a newline instead of sending
57
HARNESS
3

Support configurable inference tiers

Add provider-aware, user-selectable compute or service tiers with distinct cost, latency, and capability trade-offs, optional automatic selection, and end-to-end propagation through model and session configuration. Preserve defaults, persist choices, expose usage metadata, and never silently downgrade unsupported tiers.

Explore challenge ↗

The problem

Add provider-aware, user-selectable compute or service tiers with distinct cost, latency, and capability trade-offs, optional automatic selection, and end-to-end propagation through model and session configuration. Preserve defaults, persist choices, expose usage metadata, and never silently downgrade unsupported tiers.

Possibly addressed by:Model Tier · Tier Router · Better Model Provider

Start with these discussions

  • Feature request: end-to-end support for OpenAI Codex Standard/Fast service tiersgithub · ▲1 · 1 comments
  • User-selectable compute tiers with different token pricing for DeepSeek V4.1 Flashgithub · ▲1 · 0 comments
  • Proposal: configurable OpenAI-compatible service tier for llm-pi-ai
58
PLUGIN
3

Make settings and trajectory pages mobile-responsive

Make the web frontend, especially the settings and trajectory pages, usable on mobile screens with responsive breakpoints, single-pane navigation, touch-friendly controls, and safe handling of keyboard and safe-area constraints.

Explore challenge ↗

The problem

Make the web frontend, especially the settings and trajectory pages, usable on mobile screens with responsive breakpoints, single-pane navigation, touch-friendly controls, and safe handling of keyboard and safe-area constraints.

Possibly addressed by:Mobile Webui · Mobile · Mobile Ui

Start with these discussions

  • [Feature] Mobile-friendly web UI: responsive layout, touch support, and PWA polishgithub · ▲2 · 2 comments
  • 优化一下移动端尺寸下的界面显示github · ▲1 · 0 comments
  • Add responsive breakpoints / mobile layout to dsh-web-frontendgithub · ▲1 · 0 comments
59
HARNESS
2

Recover Sessions Rejected for Content Risk

Identify content-risk failures with metadata about the triggering historical message and category without exposing sensitive content. Provide documented recovery actions such as truncating or deleting messages and tool results, or restarting from a selected turn.

Explore challenge ↗

The problem

Identify content-risk failures with metadata about the triggering historical message and category without exposing sensitive content. Provide documented recovery actions such as truncating or deleting messages and tool results, or restarting from a selected turn.

Possibly addressed by:Session Resilience · Session Integrity · Conversation Rollback

Start with these discussions

  • 长会话被输入审核整段熔断（400 Content Exists Risk / INVALID_REQUEST）：能否提供历史定位与会话级旁路？github · ▲2 · 1 comments
  • 会话被服务端风控拒绝后永久锁死，应用内无任何恢复手段github · ▲1 · 0 comments
Last active Sep 19, 2026
2 authors2 posts · 3 reactions
60
HARNESS
3

Provide actionable, immediate sandbox failure diagnostics

Make sandbox-denied commands fail immediately with visible, streamed errors that explain the permission or namespace cause and guide users toward the correct escalation, retry, or writable-path configuration.

Explore challenge ↗

The problem

Make sandbox-denied commands fail immediately with visible, streamed errors that explain the permission or namespace cause and guide users toward the correct escalation, retry, or writable-path configuration.

Possibly addressed by:Sandbox Escalation Guard · Strip Sandbox Permissions · Sandbox Permissions Not Strictly Wider Justification Empty Fix

Start with these discussions

  • [Bug/设计缺口] workspace-write 的 bwrap user namespace 使 root 属主文件呈现为 nobody：ssh 属主检查静默失败且提权通道无归因入口github · ▲1 · 1 comments
  • [问题] 构建时沙箱拦了 vcpkg 的写入，但 cmake 直接挂死不报错，排查了半天github · ▲1 · 1 comments
  • [UX Improvement] Agent should provide clearer feedback when sandbox permission is insufficient
← PreviousPage 3 of 9Next →
x · ▲0 · 0 comments
Last active Sep 10, 2026
3 authors3 posts · 5 reactions4 comments
github · ▲1 · 2 comments
Last active Sep 8, 2026
3 authors3 posts · 4 reactions10 comments
2 authors
2 posts · 3 reactions
4 comments
Last active Sep 15, 2026
3 authors3 posts · 2 reactions4 comments
github · ▲2 · 2 comments
Last active Aug 29, 2026
3 authors3 posts · 15 reactions10 comments
hackernews · ▲0 · 0 comments
Last active Sep 18, 2026
3 authors3 posts · 2 reactions1 comments
2 posts · 6 reactions
2 comments
Last active Sep 11, 2026
3 authors3 posts · 3 reactions4 comments
github · ▲1 · 0 comments
Last active Sep 11, 2026
3 authors3 posts · 3 reactions3 comments
github · ▲1 · 0 comments
Last active Sep 14, 2026
3 authors3 posts · 3 reactions1 comments
Last active Sep 9, 2026
3 authors3 posts · 4 reactions2 comments
1 comments
github · ▲1 · 0 comments
Last active Sep 11, 2026
3 authors3 posts · 3 reactions2 comments