Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

374 plugins found

D

dsh-cursor-dev

dclef/dsh-cursor-dev

Runs the local Cursor CLI as a child coding agent from DSH - a `cursor_code` tool plus the native one-shot `cursor_subagent` tool, one mirrored DSH sub-session per run, per-task model choice, resumable conversations, a step timeline with real file diffs, and a usage, model and session panel.

35 days agoDev & Plugin ToolsMIT
B

dsh-client-ui-quote

bangbang-03/dsh-client-ui-quote

Turn any DSH selection into a reviewable quote — chat, file preview, terminal and diff; code quotes carry path#line. A sent quote keeps a source highlight and ordinal and jumps back, then joins a searchable review list with status, tags, multi-select insert, and Markdown/JSON export. Quotes collect above the composer as a 引用 ×N bar with per-chip edit and remove; side threads can bring their conclusion back to the main draft; a sent quote can be revised, with the old capsule marked superseded; replies can answer each quote by number.

36 days agoUI EnhancementsMIT
L

dsh-git

linxueyuanstdio/dsh-git

Local Git plus the four GitHub remote tabs in the official DSH right sidebar: Changes (per-file staging, line diffs, and commit messages written by the model already configured in DSH), History, then Code, Issues, Pull requests and Actions proxied by the host half. The token stays in the host half through ctx.credentials and /dsh-git/* accepts loopback requests only.

33 days agoGit & Code ReviewMIT
J

dsh-usage-stats

jockjrop/dsh-usage-stats

In DSH Desktop, see the tokens, cost and speed of every request, compare spending by model and provider, merge different names for the same model, check balances and compare real model performance.

322 hours agoUsage & BillingApache-2.0
D

dsh-telegram-bridge

datit309/dsh-telegram-bridge

Two-way Telegram remote cockpit for DeepSeek Harness: live progress tracking, screenshot vision, git diffs, shell execution, and tool approvals. Unconfigured chatId automatically claims the first sender as owner; voice-to-text requires local ffmpeg and BeeRouter services.

324 days agoIntegrations & Remote
W

portable-dsh-multi-agent-plugin

wdahah/portable-dsh-multi-agent-plugin

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

32 months agoMemoryMIT
H

dsh-git-flow

hunan36/dsh-git-flow

Branch chip in the composer tool row that switches, creates, and refreshes workspace branches, commits a checked subset of changed files with a message the session's own model writes from the diff, and pushes the current branch.

310 days agoGit & Code ReviewMIT
B

dsh-voice-call

biliye/dsh-voice-call

Voice call assistant for the DSH desktop app and the Web GUI (the same plugin, only the profile name differs): a draggable floating call ball, browser-side VAD that sends each utterance after a pause, speech recognition through the local SenseVoice model already downloaded by the official voice-input plugin (no second model), FunASR HTTP or streaming, or a cloud-compatible API, MiniMax / MiMo-V2.5-TTS (director mode and voice clone) / OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate sessions with progress, stop, and spoken completion reports.

3last monthVision, Voice & MultimodalMIT
H

dsh-git-review

haoyueqin/dsh-git-review

Review tab for DeepSeek Harness sessions: workspace changes versus HEAD or any two refs as a filterable file tree with side-by-side diffs, a lane commit graph with blame and file history, three-scope search, line comments back to the composer, and guarded stage/commit/branch/tag/stash/conflict operations.

32 months agoGit & Code ReviewMIT
G

dsh-live-canvas

goodandready/dsh-live-canvas

Renders HTML, React (JSX/TSX), Vue, SVG, Mermaid and Markdown written by the agent in an isolated iframe sandbox with SSE hot-reload, and adds a DOM click inspector, side-by-side visual diff, a responsive device matrix and one-click Vite ZIP export.

33 days agoTools & CapabilitiesMIT
H

dsh-git-sidebar

h2o-mero/dsh-git-sidebar

VSCode-style uncommitted-changes sidebar docked to the right of the DSH web conversation page: staged / unstaged / untracked file groups, status badges, per-file +/− line counts, click-to-expand diff, rename as old → new, untracked content preview, and open with the system default application.

33 months agoGit & Code ReviewMIT
A

dsh-github-router

angeloszou/dsh-github-router

Read-only GitHub access for agents, wrapping several tools. Inside the tool it automatically probes and selects whichever GitHub access method works locally, and tries network proxies on its own. That cuts down the network and parsing problems an agent may hit when accessing GitHub, and the overhead of it repeatedly trying different approaches.

32 months agoGit & Code ReviewMIT
L

dsh-plugin-heartbeat

littleblacktong/dsh-plugin-heartbeat

Autonomic heartbeat for each root agent: silent pulses diff the session's todos, Agent Team board and goal against what the last pulse saw, and speak only on a signal — L1 report, L2 ask (ask_user_question), L4 escalate — never starting work. Each message carries a why-now line, an optional one-line physiology signature (time since your last message and how many times it has reached out today) and a compact task snapshot (800-char cap); a dedupe window, quiet hours, a daily budget, refractory/restart cooldowns and persisted vitals keep it quiet, while busy-safe followup injection never stacks. It shares one advisory speech floor with dsh-plugin-memory (~/.dsh/proactive-cooldown.json, 180 s) so the two never talk over each other, stays silent while a child subagent or teammate is still working, and surfaces a "subagents working · N" pill in the conversation header (polling pauses while the tab is hidden). v0.8 adds a diagnostics panel that explains recent quiet pulses and names the current speech-floor holder, plus panel controls for the arbitration window, presence suppression and the physiology line; its settings section carries a stroked heart mark (16×16, stroke 1.3, same spec as dsh-plugin-memory). v0.8.1 makes the plugin compatible with DSH 0.2.2-rc.2: the agent registry is read with agents.roots() when available and falls back to agents.list() on rc.2, and every agent/created listener is exception-guarded — on rc.2 an unguarded throw there rejects agent registration and no session can be created, so rc.2 users must upgrade to 0.8.1 or newer.

35 days agoWorkflow & AutomationMIT
Y

dsh-editor

yangshen830-eng/dsh-editor

VS Code-style code editor: sidebar file tree over the workspace, Monaco editing, file read/write, Git status and diff, search, and Markdown preview.

33 months agoUI EnhancementsMIT
K

dsh-captain

kanonouta/dsh-captain

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

33 months agoWorkflow & AutomationMIT
K

dsh-packer

klrsl/dsh-packer

Agent config packer for DeepSeek Harness: pack local agent assets (skills/sessions/profiles/settings/memory) into a zip for migration or sharing, with privacy scanning, diff-based restore, pack management, and a settings UI; memory ships as a read-only Markdown mirror, not the live database.

3yesterdayTools & CapabilitiesMIT
T

dsh-plugin-git-workflow

truelove-dreamer/dsh-plugin-git-workflow

First-class Git tools for the model: status / diff / log / commit / branch with validated messages and paths - no bare-shell git calls.

33 months agoGit & Code Review
O

dsh-tool-diff

omdsh-dev/dsh-tool-diff

Structured comparison and unified diffs for text/JSON/CSV/Markdown.

32 months agoTools & CapabilitiesMIT
K

dsh-plugins (dsh-dev-git-graph)

kp-z/dsh-plugins

A Git Graph tab for DSH Web: a faithful port of vscode-git-graph 1.30.0 that registers a native tab in the dsh-better-sidebar right rail (prerequisite), auto-binds to the session workspace, runs the full git operations (checkout/merge/rebase/push/tag/stash) directly on the host, and opens file diffs in the built-in DiffTab.

2yesterdayGit & Code Review
W

dsh-wdx-git

wdxtub/dsh-wdx-git

Git inside your DSH session: a right-sidebar panel for the current workspace and a global page listing every workspace, one sync button that becomes Fetch, Pull, Push, Publish branch or Sync, a commit tab that opens first with every change checked, AI-written commit messages from the staged diff, plus history, branches, stash and in-panel conflict resolution.

23 days agoGit & Code ReviewMIT
V

dsh-prompt-optimizer (bundle)

viewway/dsh-prompt-optimizer

Prompt optimizer for the DSH composer. One click runs rewrite then self-review rounds over the draft with per-round diff preview, and a rejected result rides into the next round as a prior attempt. Five fixed re-run directions (more concise / more detailed / more technical / restructure / stronger acceptance); a 164-role library ships in the package, roles recommended by draft or picked explicitly; matched installed skills fold into the meta-prompt under exact-name constraints; results save to a prompt library (browse, insert, re-optimize, two-step delete); mechanical acceptance criteria carry an executable check-command template; output language follows the agent UI language.

23 days agoUI EnhancementsApache-2.0
J

dsh-plugin-syncup

jijijitian/dsh-plugin-syncup

Keeps plugin inventories in sync across machines through a secret GitHub Gist, and updates installed plugins to their newest npm or GitHub release. Push shows a diff first: version conflicts default to the newer side, entries only the Gist has stay by default, and entries only the local machine has are pushed. Each update can pick the npm or the GitHub channel, and every install goes through the plugin manager with a live log.

26 days agoDev & Plugin ToolsMIT
C

dsh-gitlab-panel

caimc21069065-prog/dsh-gitlab-panel

GitLab panel in the DSH right sidebar: commit graph, branches, changes, merge requests (inline diffs, review submission, pipelines), issues, and agent tools with an approval queue for triage and batch actions. GitLab data needs a personal access token or a logged-in `glab`; local git data works without either.

215 days agoGit & Code Review
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