Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
Feishu (Lark) OpenAPI MCP connection for DeepSeek Harness: drives the official @larksuiteoapi/lark-mcp stdio server with your Feishu app credentials, exposes Feishu API tools (IM messages, Bitable, docs, calendar, drive) under mcp__feishu__*, and a web settings panel
Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhengjy01/dsh-feishu-mcp
DSH plugin: Feishu (飞书) custom-bot notifications when an agent session settles (idle) or asks for input (ask_user_question). Adapted for DSH 0.1.0-rc.7 (@deepseek-ai/cordis line).
Control your DeepSeek Harness agent from Feishu/Lark: send tasks via DM, receive results back, approve tool calls from mobile cards. Powered by lark-cli.
Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ShiXiangYu2/dsh-feishu-remote
Adds a search box to the 'Fetch available models' candidate dialog in DSH Settings — pure browser-side DOM enhancement, no component modification. 为「设置→模型→获取可用模型」候选弹窗增加搜索过滤,纯浏览器半增强,不改任何组件代码。
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:masknull/dsh-fetch-models-search
Safe third-party web fetch for dsh: delegates page retrieval to a user-configured third-party service (Tavily / Jina / Firecrawl / custom crawler via contract v1) so the local machine never connects to arbitrary URLs (no SSRF surface). API key lives only in the managed credentials store; per-session fetch budget caps usage; a bundled Crawl4AI stack can be auto-managed.
Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tallahandsome-ux/dsh-fetch-third-party
Fuzzy file finding and indexed content search for DSH: find_files / resolve_file / related_files / fff_grep. Pure-JS path index + subsequence scoring (no native dependencies). Port of pi-fff for the Pi coding agent.
Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sleepinginsummer/dsh-fff
Composer file attachment for DeepSeek Harness Web: a paperclip button opens the DEVICE file picker (any file type); uploaded files show as chips in the composer's top-left, laid out left-to-right; the reference line is auto-carried into the draft so no @ mention is ever needed.
Drag or paste files or pictures into the DSH Web composer as one scrolling row of chips inside the input box — the form Doubao uses — with the files sent as @path references
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:RCYD857/857-dsh-file-attach
Beam files from your desktop into the agent's context: drag onto the DSH Web composer, resolve the real absolute path by name (workspace + Downloads/Desktop/Documents), pick a candidate chip, and beam it in — no copy, no path text in the composer. On submit the Host injects the paths into the agent request as a hidden plugin-notice message; the agent reads the source file directly.
Raw-file SHA-256 and SHA-512 verification tool for DeepSeek Harness
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yan9651688/dsh-file-checksum
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.