Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

432 plugins found

G

claude-in-dsh

geekricardo/claude-in-dsh

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in place of the access-mode selector, and permission requests, AskUserQuestion and ExitPlanMode routed to the native DSH approval, question and plan-review cards. The stream is written as native DSH session events, so the built-in transcript, tool cards and nested subagents render it; Claude slash commands merge into the command palette; the CLI is held by a detached broker, so plugin updates and DSH restarts do not interrupt a running turn.

35 days agoModels & ProvidersMIT
B

dsh-GreaterClarity-plugin

baisbt/dsh-greaterclarity-plugin

Enhances the DSH web session view — one-click collapse of reasoning and tool chains, numbered history quick-jump, Markdown export, AI avatars.

33 months agoUI EnhancementsMIT
H

dsh-sidebar-assistant

hufeide/dsh-sidebar-assistant

A sidebar assistant plugin for the Web interface, allows users to select any text, displays the model’s reasoning process and final answer in a floating panel.

33 months agoUI Enhancements
A

dsh-models-dev-reasoning

aerince/dsh-models-dev-reasoning

Adds models.dev reasoning levels to unconfigured third-party DeepSeek Harness models.

325 days agoModels & ProvidersMIT
J

dsh-reasoning-settings

junelearn/dsh-reasoning-settings

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度,并可为每次子 Agent 调用选择模型|Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

33 months agoModels & ProvidersMIT
O

dsh-gpt-adapter

oh-dsh-plugins/dsh-gpt-adapter

DeepSeek Harness plugin for GPT models and Codex instructions, skills, plugin resources, and MCP configuration.

23 days agoMCP & ConnectorsMIT
H

dsh-gatekeeper

huajikano/dsh-gatekeeper

Inspects the model's streamed reply before it is committed and either discards it or holds it for review when it reads as a refusal, so that text does not stay in the session context. Detection combines built-in phrase rules (an opening refusal, a capability denial, policy wording, first-person intent, refusals quoted in reasoning) with a plain-text word list and optional regular expressions. Interception can sit at the llm/stream waterfall, at the HTTP fetch layer before encryption (not TLS decryption, and it cannot tell which session a call belongs to), at both, or in a preview mode that shows a transient preview while the original chunks stay in memory until the whole reply has been checked. The same plugin also guards tool calls on tools/pre-execute: a command that deletes a drive, filesystem or user-profile root, formats or repartitions a volume, empties the Recycle Bin, fetches and executes a remote script, or writes to a raw device is denied, and a recursive delete outside build directories is recorded by default. Each tier can be set to deny, ask, record, or off, and the disk guard has its own switch. Both halves are heuristics: they can miss phrasings, the disk guard sees the arguments of a call rather than what a running script does, and they fail open.

23 days agoSessions & Messages
Z

dsh-plugins (dsh-opencode2api)

zhiqiangme/dsh-plugins

Runs the standalone opencode2api backend (jasonxu114514/opencode2api, Windows x64/ARM64, no Docker or OpenCode CLI) with DSH and on exit stops only the process it launched; its settings card installs, updates or rolls back the backend from checksum-verified GitHub releases, copies the initial admin password and syncs /v1/models into an opencode2api provider with context, vision and reasoning efforts, re-syncing every 10 minutes. Frozen archive: 26.10.31 is the last version, and the author points to dsh-magpie as the replacement.

223 hours agoModels & ProvidersMIT
X

harnessmm-dsh

xiuxiu-6/harnessmm-dsh

Guarded decision reuse for the DeepSeek Harness: the model authors already-decided tool actions once, and receipt-supported ones execute through the native tools without another reasoning request. Ships a read-only decision-reuse panel with per-number dat

211 days agoWorkflow & AutomationApache-2.0
F

dsh-2d-model-picker

fyerl/dsh-2d-model-picker

Select a model and its reasoning effort in one drag with a two-dimensional grid.

211 days agoUI EnhancementsMIT
L

dsh-local-trim

leonlee114514/dsh-local-trim

One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.

22 days agoModels & ProvidersMIT
T

dsh-model-visibility

tzyceng/dsh-model-visibility

Manage which models appear in the composer model menu. A settings page lists every provider's models with a per-model switch, provider-level show/hide, collapsible groups and filters by kind; switched-off models leave the menu while the model in use in the current session stays. The list can be searched by name or ID and filtered by capability (multimodal, reasoning) and by minimum context window (128K / 256K / 512K / 1M). Rows show the model kind, and chat models also show reasoning support with the adapter's effort levels, their context window and input modalities. Labels merge manual overrides, the settings document, the adapter, the relay's GET /models response, a built-in pi-ai / models.dev catalog, name inference and vendor corrections in that priority order, with the source named on hover and dashed borders marking inferred values. Any model can be edited by hand (kind, context window, modalities, effort levels); those edits are stored outside the profile and can be written back into the model provider's settings. A hard re-fetch drops every cache and asks the adapter and all relays again. A switch, on by default, lets relay routes whose models declare text-only input accept images in memory, without editing configuration files. The hidden list is stored in the profile patch and mirrored to $DSH_HOME.

23 days agoUI EnhancementsMIT
Z

dsh-plugins (dsh-magpie)

zhiqiangme/dsh-plugins

Manages a Magpie model list and writes the checked models into a Magpie provider group: full sync from /v1/models, manual entries, per-model context, output limit, image input and reasoning efforts, sorting and drag reordering. On Windows x64/ARM64 it also downloads and upgrades Magpie from yetone/magpie-releases with SHA-256 verification and rollback, auto-upgrades once a release is 30 minutes old and all conversations are idle, starts Magpie in the tray with DSH, and toggles its lite mode and sleep prevention.

223 hours agoModels & ProvidersMIT
Y

dsh-claude-effort-slider

youqisibun/dsh-claude-effort-slider

A six-stop reasoning-effort slider for DeepSeek Harness, with a pixel-texture Ultracode mode that sweeps in from right to left and adapts to light and dark themes.

219 days agoUI EnhancementsMIT
G

dsh-novel-fish

gongfpp/dsh-novel-fish

Read local EPUB, TXT and Markdown novels below selected native DSH chat regions on explicit expansion, preserving real reasoning and tool output without sending novel text to the model. Requires DSH >=0.2.1-rc.2 <0.3.0-0.

217 hours agoJust for FunMIT
P

dsh-auto-model-routing

prgrmrwy/dsh-auto-model-routing

Use Jev to adjust main-chat reasoning effort without switching its model, independently select and apply fresh sub-agent capability and effort, and inspect decisions with per-reply allocation feedback.

26 days agoModels & ProvidersMIT
G

dsh-subagent-models

garybot126/dsh-subagent-models

Set the provider, model and reasoning effort delegated subagents run with, from one chip beside the composer: a per-conversation override and a profile-wide default share the same two controls, and the chip always shows the effective route. Applied when each in-process child is created (agent/created + agent.model.select()); no settings page, no preset edits, no model-facing tool parameters.

27 days agoModels & ProvidersMIT
H

dsh-default-model-lock

hzsfn/dsh-default-model-lock

Keeps the shared default model pinned, so switching the model inside a chat no longer rewrites the global default and no longer lowers that default's reasoning effort.

214 days agoModels & Providers
F

Trae2api-dsh

fusheng-cs/trae2api-dsh

Use TRAE account model quota in dsh, with multi-account management, daily check-in, rotation, usage statistics, reasoning levels and model visibility. Requires Python 3.10+; the first run downloads Python dependencies.

2last monthModels & ProvidersMIT
A

dsh-reasoning-effort-new

ayowait/dsh-reasoning-effort-new

Fork of dsh-reasoning-effort with a two-level model picker in the composer: a provider list, a model pane that slides out beside it, search, and compact rows, alongside the reasoning-effort slider and its max-level effects.

2last monthModels & ProvidersMIT
6

dsh-model-auto-enricher

66rapper/dsh-model-auto-enricher

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.

218 days agoModels & ProvidersMIT
T

dsh-grok-xai

tudoupn/dsh-grok-xai

DeepSeek Harness plugin for SuperGrok and X Premium subscriptions: device-code sign-in, the xai provider, account-visible chat models with context and per-million-token prices, reasoning efforts read from model capabilities, and subscription usage.

214 days agoUsage & BillingMIT
G

dsh-prompt-suggestion

goldenloaf24h/dsh-prompt-suggestion

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

227 days agoUI EnhancementsMIT
F

dsh-model-picker

findly-qwb/dsh-model-picker

Two-pane model picker that replaces the composer model menu with a searchable provider-grouped list on the left and a detail card on the right showing the selected model's context window, output cap, capability tags and reasoning-effort levels, all read from that model's own provider. The npm name dsh-model-picker belongs to another author; install through this GitHub source.

212 days agoUI EnhancementsMIT