Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
Run opencode as an ACP subagent inside DeepSeek Harness: a delegation tool, a settings page, and a run history with opencode session ids and token usage.
Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangqingdhuo/dsh-opencode-acp
Pre-probed OpenCode Go / Zen model routes for DeepSeek Harness — every model is really called once, the verdict is written into its picker name, the region-blocked ones are routed through your local proxy automatically, and the official dsh-opencode-go companion comes with it.
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fffcodefox/dsh-opencode-doctor
DeepSeek Harness plugin: gives a text-only model eyes. It mounts the bundled opencode-eyes MCP server, which sends an image file to StepFun's step-3.7-flash vision model and returns a detailed description, as the tool mcp__opencode_eyes__describe_image.
Vision tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bauerelizabeth07139/opencode-eyes
DeepSeek Harness plugin: eyes for text-only models through NVIDIA NIM. It mounts the bundled opencode-eyes-nvidia MCP server, which sends an image to a hosted vision model (MiniMax-M3 by default) and returns a description, exposing mcp__opencode_eyes_nvidia__describe_image and mcp__opencode_eyes_nvidia__list_vision_models.
Vision tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bauerelizabeth07139/opencode-eyes-nvidia
OpenCode gateway provider for DeepSeek Harness: one route to the local opencode-api-plugin gateway, one route to an inlined opencode2api local proxy (Zen free tier), with a curated model registry and a model-manager settings page
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EDDY597/dsh-opencode-gateway
Self-maintained OpenCode Go model catalog for DeepSeek Harness: protocol-separated sibling routes (extras/responses/messages) via the settings.mutate seam, with live-synced reasoning efforts. Never touches the built-in opencode-go route.
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AincradLabs/dsh-opencode-go-catalog
DeepSeek Harness plugin for the OpenCode / OpenCode Go routes: declares the route wire protocol, keeps the DeepSeek V4.1 models at the front of the model list, and attaches a stable per-conversation x-opencode-session header (fixes 400 MissingSessionID) without leaking the internal session id.
Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:itchenshi/dsh-opencode-go-path
OpenCode Go model provider for DeepSeek Harness — a maintained fork that keeps the live model catalog reachable when another adapter already owns the opencode-go route, no longer drops models belonging to families the catalog has not seen before, and configures itself from the Settings → Models page instead of a settings section of its own
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:HaydenSmith1121/dsh-opencode-go-plus
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.