Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1085 plugins found
dsh-balance
geekricardo/dsh-balance
Composer-dock balance/usage readout for DeepSeek, Kimi Coding, OpenCode Go, Zhipu, MiniMax, OpenRouter and OpenAI Codex — provider-based, 2s polling, 5min cache.
parallel-npm-packages
parallel-web/parallel-npm-packages
Parallel Search provider for DeepSeek Harness
dsh-firecrawl
firecrawl/dsh-firecrawl
Firecrawl-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web)
dsh-opencode-zen-free-provider
jiesou/dsh-opencode-zen-free-provider
OpenCode Zen free models provider for dsh
dsh-vision-recognizer
kaixinbaba/dsh-vision-recognizer
Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.
dsh-vision (vision-route)
314857493/dsh-vision
Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.
keyringseam
fieldnote-ops/keyringseam
macOS Keychain credential provider that replaces the local-file provider and uses a signed, notarized universal helper.
dsh-codex-provider-plugin
damonbao/dsh-codex-provider-plugin
OpenAI Codex OAuth provider and native settings UI for DeepSeek Harness
dsh-commandcode-go-provider
jiesou/dsh-commandcode-go-provider
Command Code Go provider adapter for dsh: scan the Go-plan model catalog dynamically and serve /alpha/generate through the harness LLM seam
dsh-dashboard
uddoo/dsh-dashboard
A Symphony-compatible multi-provider task orchestrator and dashboard for DeepSeek Harness
llm-adaptive
dylan121322/llm-adaptive
Adaptive model routing: per-request complexity classification with automatic provider routing.
dsh-subagent-cwd
lynx-gt/dsh-subagent-cwd
Extends dsh-subagent-tools with a per-call cwd for subagents, shipped with the two in-process provider patches it requires.
dsh-subagent-tools
lynx-gt/dsh-subagent-tools
Per-call model, provider, persona, and toolFilter overrides for subagent delegation, with @preset: references and provider/model composite ids.
dsh-voice-hotkey
whiplashf/dsh-voice-hotkey
Push-to-talk remote for the official Voice Input bundle: a hotkey (default Alt+V) starts and stops its recorder — tap to toggle, or hold 0.5 s and release to stop like a walkie-talkie. An energy-based VAD ends the take after a configurable silence (0.5–10 s), and the caret is moved into the composer before recording so the transcript lands there and Enter sends it. Optional auto-send, a second hotkey that focuses the composer, a provider picker in the composer toolbar, and both hotkeys can be rebound or cleared. Recording, transcription and insertion stay in the official bundle; audio goes only to your own DSH server. Zero runtime dependencies.
dsh-mistral-vibe-provider
khuraie/dsh-mistral-vibe-provider
Mistral Vibe Code as a DSH provider route — PKCE browser sign-in, the live model catalogue with per-model prices, the Vibe Code and Studio/API budget meters in Settings and the sidebar, and a per-session cost figure in the composer. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-fallback-router
hongxin-y/dsh-fallback-router
Per-model routing for DeepSeek Harness: fallback chains (official or loop), time-slot windows, per-provider retry policies, and failure rules by error code, regex, or structural markup detection.
dsh-radeon-capacity
lcy362/dsh-radeon-capacity
Shows AMD Radeon Cloud AI Capacity for every Radeon model — a per-model badge in the model picker, and the selected model's capacity on the same row as its name. The badges register only once a Radeon provider is configured, so they never displace the host's own model annotations. Quota is display-only, since AMD is currently free and unmetered. Its settings page can also write the provider into the DSH user layer, so the provider keeps working after the plugin is uninstalled. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-volc-balance-card
awenjackson/dsh-volc-balance-card
Persistent sidebar card for your Volcengine recharge balance and Ark Coding/Agent plan windows, with in-card AK/SK setup and per-provider toggles.
dsh-jev-mcp
ningyuanlee/dsh-jev-mcp
Run the Jev MCP server inside DeepSeek Harness. Typed judgment tools (verify, screen, find, review, gate, and the rest) register as mcp__jev__*. Provider keys stay in DSH credentials. Jev is not a chat model.
dsh-compact-arsenal
tacitsay/dsh-compact-arsenal
Configurable context compaction with three independently switchable sections — whole-context checkpoint, reasoning compression and tool-output pruning — each with its own pressure threshold and method. Mechanical modes make no model calls; model modes summarize fragments in batches with a configurable provider and prompt. A left-sidebar panel exposes switches, method cards and editable parameters that save without a restart, and every rewrite is archived with its original text.
dsh-github-copilot-accounts
jacobcodeshow/dsh-github-copilot-accounts
Multi-account manager for GitHub Copilot in DSH: device-code sign-in for GitHub.com and GitHub Enterprise Cloud tenants on `*.ghe.com`, one-click account switching, per-account plan and AI credits display, and a preset Copilot provider route with first-login model catalog fallback.
dsh-fps-workbench
blacstar7/dsh-fps-workbench
Four-pointed star (FPS) adds long-task status, tool summaries, session outputs, persistent attachment drafts, native voice integration, provider usage, compatibility checks, and optional image generation to DSH.
dsh-plugin-strata
youshanlian/dsh-plugin-strata
Integrated control plane for the local strata model stack: manage the strata-hop :8080 model-switching router (status/models/warm/logs), stream live model-switch and load state into the web GUI status chip and the strata_status tool, preload a model engine the moment it is selected, edit run-config and shared chat settings from a GUI tuning panel or strata_params, and ship the dsh provider patch that routes chats to the router with Effort-level mappings. Read-only toward inference: it never sends a prompt and spends no tokens; bring your own running strata plus strata-hop (defaults :8080 hop, :8756 monitor). As shipped, the status server listens on 0.0.0.0:8756 with no authentication and open CORS, and its endpoints can change run-config and restart the engine; set host to 127.0.0.1 in cordis.patch.yml to keep it on this machine. It expects strata-hop as a systemd user unit.
dsh-decide
calmzeala/dsh-decide
Connects DSH to decision models (TypeSafe Jev, TokenRhythm NeoHorse-Jev, OpenAI Decisions, and local System One endpoints) with decide, gate, rerank, and judge tools plus a settings page. Needs an API key for at least one provider (kept in the DSH credential store); the text you ask it to judge is sent to the selected provider unless it is local. The command guard is off by default.