Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1085 plugins found
dsh-moa-native
ddl095/dsh-moa-native
Native generation-time Mixture-of-Agents: every turn, reference models run the same session context in parallel as pre-run drafts and one aggregator executes with full tooling; config-as-model recipes, F mirror / R trimmed views, enforced subagent gating (dual-shape session indexing), derived per-recipe vision (vision refs relay image reads to text-only aggregators), tiered cadence with separate steering and patrol rosters plus frozen reuse between beats, degeneration guard dropping degenerate reference output, anonymized model face (failure notices carry no provider identity), and cache-friendly guidance placement (the rehearsal record is pinned where it was produced instead of appended to every request, so the cached prefix covers it and each step pays only for what was added since - on by default across every cadence).
dsh-mojie-model-provider
mojieaigc/dsh-mojie-model-provider
Adds Mojie (mojieaigc.com) as a DSH model provider, so its models appear in the model picker, and registers the native image tools plus the /image command for generation and editing.
multi-role-groupchat (multi-role-groupchat)
zhdzh-good/multi-role-groupchat
Multi-role group chat panel for DeepSeek Harness: join as one character, chat with 2-3 AI members, route replies by addressee with probabilistic bystanders, use @ handoffs, and keep private memory/relationships, a global character library, failure diagnostics, retry of failed replies, message search, a sticky scene note, paged long-history rendering, cross-tab sync, provider-catalog models, and JSON import/export.
dsh-balance-widget
breey05/dsh-balance-widget
Shows the selected provider's balance below the Harness composer and estimates spend from observed balance drops.
dsh-claude-code-provider
jk89/dsh-claude-code-provider
Claude Code (the official, unmodified binary, via the Agent SDK) as a model provider and subagent inside DeepSeek Harness
dsh-cpamc
aicivilization/dsh-cpamc
Model provider for DeepSeek Harness (DSH): WorkBuddy, Trae, Qoder, ZCode and your Claude / Codex subscriptions behind one OpenAI-compatible endpoint, with a lightweight settings panel and the full management interface one click away. · DSH 的模型提供方:设置页轻量管理,
dsh-official-cleanup
tkhs101/dsh-official-cleanup
DeepSeek Harness Web UI cleanup: a direct Settings launcher instead of the sidebar 更多 menu, no unusable official DeepSeek provider card, and the official-model Session-log upload pinned off. · DSH 界面官方入口清理
dsh-opencode-provider
goodandready/dsh-opencode-provider
OpenCode Console and OpenCode Go provider for DeepSeek Harness.
dsh-sandbox-mxc
bitsmug/dsh-sandbox-mxc
DeepSeek Harness sandbox provider backed by MXC (Microsoft eXecution Containers): wraps ctx.sandbox.confine() argv as `wxc-exec --config-base64 <policy> -- <command>` on the BaseContainer backend. One runtime dependency (@microsoft/mxc-sdk, for the wxc-ex
dsh-plugin-devin
quonaro/dsh-plugin-devin
Devin CLI inside DeepSeek Harness: a `devin` delegation tool, a /devin command, and a `devin` LLM provider route — all over the ctx.subprocess seam.
dsh-plan-act-models
cynthiayx/dsh-plan-act-models
A mode dropdown in the composer that switches models through the host's own session.selectModel — Plan, Act and any number of user-defined modes, each with its own provider, model, reasoning effort and optional instruction that joins the system prompt while that mode is active — plus a soft switch into Plan mode and a forced switch to Act when a plan is approved, with per-workspace overrides for Plan and Act.
dsh-api-hub
limooning/dsh-api-hub
API Hub — manage and call local API providers (keys, models, balances) and skills from inside DeepSeek Harness
dsh-model-picker
2424830124/dsh-model-picker
A searchable, provider-grouped replacement for the DSH composer's model picker.
dsh-agent-foreman
dclef/dsh-agent-foreman
Parent-agent dispatch with review: split a task into work orders, hand each to a contractor you picked (its own provider, model, and reasoning effort), then pass or fail every delivery — failed ones are re-dispatched with your feedback.
dsh-agent-settings
swordx-lu/dsh-agent-settings
Agent Settings: manage reusable sub-agent profiles in the sidebar, each with a when-to-use description and its own provider/model route, and let the agent start the matching one as a subagent.
dsh-muse-code
thestreamcode/dsh-muse-code
Adds Meta's Muse Code subscription as a DSH model provider: the bundle declares the shipped Meta route under Settings > Models, syncs the account chat catalog (Muse Wonder included) into the model picker, and adds a Sign in card plus the /muse-login command that run DSH's built-in Meta device-code flow, keep the minted key renewed, and show a red or green credential dot. Needs an active Muse Code subscription and no Meta CLI.
dsh-workbuddy2api-hub
hima6652/dsh-workbuddy2api-hub
Registers the models of a local workbuddy2api-hub gateway into DSH as one OpenAI-compatible provider per gateway API key, each key keeping its own model selection, and shows the main key's credit balance plus today's and this week's tokens, credits and API-equivalent cost in a sidebar badge. Requires workbuddy2api-hub running locally.
dsh-routing-forensics
bushizhanghan/dsh-routing-forensics
Forensic analysis of past model-routing decisions. Replays each session, classifies every turn's task complexity from its request shape (deterministic, no LLM), and reports two kinds of waste: an expensive model on cheap work (the difference is measurable), and a cheap model on expensive work that failed on its own merits — where every retry re-sends the whole context, so the downgrade cost more than the upgrade. Distinguishes provider-capacity retries (RATE_LIMIT/TIMEOUT/TRANSPORT) from model failures so it does not cry wolf. Derives routing rules from the evidence, priced against a built-in per-million table.
dsh-plugin-nuaa-search
oxygen640/dsh-plugin-nuaa-search
Zero-key web search provider for the built-in web_search tool: scrapes Bing China, 360 and SearXNG through a backend fallback chain and returns real URLs with snippets and publish dates. No API key and no settings card are required. SearXNG is used only when you set your own instance URL, and installing this plugin switches web_search to it and turns off the official DeepSeek search row.
dsh-sensitive-replace
short-arm-ape/dsh-sensitive-replace
Sensitive-character replacement for DeepSeek Harness: matches messages and tool results against a YAML blocklist you maintain (global, per provider id, or per model) before the model reads them, and scrubs the outgoing request again before dispatch, so blocked characters cannot trip the official API Content Exists Risk 400.
dsh-ai-providers (dsh-ai-typesafe)
firefox2100/dsh-ai-providers
TypeSafe AI Jev decision provider for typed probabilistic choices and scores in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.
dsh-ai-providers (dsh-ai-ollama)
firefox2100/dsh-ai-providers
Ollama provider for language models and embeddings, with model discovery, loading, and unloading in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.
dsh-ai-providers (dsh-ai-dashscope)
firefox2100/dsh-ai-providers
Alibaba Cloud DashScope provider for Qwen language models, embeddings, reranking, speech, and image generation through native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.
DSH-Plugins (2.3.0)
ccl4-56-23-5/dsh-plugins
Manage API providers and enabled models, with provider-grouped model switching and keyword search in the native model menu.