Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

437 plugins found

J

dsh-linked-workspace

jiahui-huang1/dsh-linked-workspace

SSH-backed remote directories and linked local⇄remote workspaces: read-only remote browsing, an editable linked workbench, bidirectional SFTP transfer, mirroring and a linked_workspace tool. Sidebar pages require the dsh-better-sidebar plugin (v0.24+); without it only the Settings pages load.

22 days agoIntegrations & RemoteMIT
A

dsh-agents-viewer

atrestandbed-bot/dsh-agents-viewer

View and edit the AGENTS.md / CLAUDE.md instruction chain in a native right-sidebar tab — global, shared, and every project directory down to the session working directory — with in-place save that creates missing files, a chat-header toggle, and an /agents command that works without the panel.

22 days agoUI EnhancementsMIT
S

dsh-agents-md

sillykjs/dsh-agents-md

Adds an Agent docs tab to the conversation view: it lists the AGENTS.md and CLAUDE.md instruction files DSH actually loads for the current session (the ~/.dsh and ~/.agents roots, plus every directory from the project root to the working directory), previews each as Markdown with per-file sizes and the 64 KiB instruction budget, edits and saves them in place after a sha256 version check, and opens the workspace folder from the path button; a saved file takes effect on the next message.

212 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
L

dsh-adapt-packs

lugabeeee/dsh-adapt-packs

Adaptation packs for third-party DSH plugin panels on phones — 44px touch floor, width reclaim, shell hit targets and floating-widget clearance — loaded by the dsh-mobile plugin from its extensions directory (dsh-mobile must be installed for them to take effect), with a settings page that installs them and a per-plugin compatibility list.

28 days agoUI EnhancementsMIT
1

dsh-video-skills

1368546410qq/dsh-video-skills

Browses the awesome-claude-video-skills catalog (373 entries) inside DSH settings and installs a chosen skill into ~/.claude/skills and/or ~/.dsh/skills: it downloads the GitHub archive of that repository and copies the skill directory, and executes no code from the repository. Installs run as background jobs with live progress (bytes downloaded, files copied) and can be cancelled; skills installed by the plugin can be uninstalled, while directories without its marker are left untouched. Rows show an approximate repository size reported by GitHub. The same actions are exposed to the agent as the video_skill_search, video_skill_install and video_skill_uninstall tools.

24 days agoSkillsMIT
T

dsh-project-groups

thinkofrain1213/dsh-project-groups

DSH plugin: group sidebar sessions by project (a label, not a directory), give each project a work document whose format follows a spec, register its related links, and show the exact runtime-context injection on the settings card.

220 days agoSessions & MessagesMIT
Z

dsh-skills-mcp-manager

zx2021210538/dsh-skills-mcp-manager

Forked from j62268781-alt/dsh-skills-mcp-manager (MIT) at its 0.5.6 baseline and substantially reworked since; it registers the same plugin id, so it cannot be installed alongside the original. Adds lossless cordis.patch.yml writes (JS expression values preserved), save-gated per-tool filters, skills governance over the DSH roots plus 10 external agent directories with per-skill/per-source switches enforced through the agent-scope skills provider (disabling actually hides a skill from the model), categories and a restorable trash, GitHub-repository install/update/rollback, zip and SKILL.md import, skills.sh/ClawHub market, workspace view, sidebar panel, dark/light contrast fixes, and update checks against the published npm package (same source as market installs; npm publication carries OIDC provenance).

27 days agoUI EnhancementsMIT
M

dsh-skills-console

morehao/dsh-skills-console

Lists the skills in the shared skills directory with their source and version, installs and updates them from a GitHub repo, removes them to a recycle bin kept for 7 days, and controls which agents can see each skill and whether the model may invoke it.

23 days agoSkillsMIT
M

dsh-pouch (dsh-hooks)

moon16u/dsh-pouch

File-defined command hooks across the session, prompt, tool, permission, Stop and PostCompact seams, with an approval-only GUI: no unapproved command runs, and approval binds the exact definition, canonical working directory and pinned watchFiles. Commands run as the DSH OS user without a hook sandbox, so the trust ledger is explicit.

24 days agoSecurity & PermissionsMIT
Z

dsh-notes-plugin

zxy0902/dsh-notes-plugin

Notes and folder reader in the main panel: a file tree with pinned files, closeable tabs, Markdown split edit/preview with synced scrolling, plain-text editing, manual save, and drag-to-move. Deleting a file moves it to the system trash where one exists (macOS, Linux), falling back to an in-folder dsh-notes-trash directory; Windows has no delete entry.

211 days agoTools & CapabilitiesMIT
K

dsh-butler-archive

kira905/dsh-butler-archive

DSH web plugin that browses, previews, restores and deletes archived sessions that were moved out of the sessions directory.

27 days agoSessions & MessagesAGPL-3.0
A

dsh-ssh-workspace

ahian-lee/dsh-ssh-workspace

SSH workspaces for Windows DeepSeek Harness Desktop 0.2: discover OpenSSH hosts, add or browse remote project directories, and route file, search and Bash operations by workspace while the DSH runtime stays local. A Desktop compatibility fork of Yan-Zero/dsh-remote-ssh that preserves local permission defaults.

227 days agoIntegrations & RemoteApache-2.0
S

dsh-skill-compat-plus

shuxidemosheng/dsh-skill-compat-plus

Mounts external skill directories (Claude Code, Codex, ZCode) into DSH as read-only skill providers: frontmatter field mapping, name slug normalization and hot reload.

2last monthTools & CapabilitiesMIT
X

dsh-user-memory

xinzeqing/dsh-user-memory

White-box memory in two parts: four user-authored long-term tiers (must-follow rules, behavior settings, user profile, optional rules) injected as one system-prompt section, plus a separate temporary working set (cross-session handoffs, stage goals, waiting items) with its own 1200-character budget that stops being injected once an entry is done. The long-term tiers are plain Markdown files the user can read and edit; the agent can only propose them, and nothing is written until the user accepts in the Chinese panel. Temporary entries are written only when the user explicitly asks, and live in <DSH_HOME>/temp-memory.json (created on first write), not in the memory directory. No auto-capture, no background writes, no network.

24 days agoMemoryMIT
X

dsh-sidebar-enhancement

xmwengxing/dsh-sidebar-enhancement

Enhanced right-sidebar files panel: rename, create, upload, download (a directory is zipped on the fly), copy the full path and delete from the tree; an editable document renderer for 128 text extensions with Ctrl/Cmd+S save and conflict detection; plus an independent bottom terminal panel with tabs and a quick-command library persisted under the DSH home.

220 days agoUI EnhancementsMIT
L

dsh-novel-reader

laoganr/dsh-novel-reader

Local TXT novel reader in the DSH right sidebar: bookshelf with file, directory and path import, chapter table of contents with jump, click-to-turn or vertical-scroll paging, reading progress restored across restarts, and font, line-spacing, background and night themes.

2last monthUI EnhancementsMIT
N

dsh-workspace-combiner

ninglovegithub/dsh-workspace-combiner

Multi-workspace manager: bind a docs anchor plus ordered code-project repositories into one session, injecting their absolute paths, a recursive file index, a server/client endpoint index and optional coding standards, and syncing writable directories into the sandbox.

27 days agoUI Enhancements
J

dsh-projectless-session

jarvisluk/dsh-projectless-session

Adds a Session without workspace entry to the DSH Workspace picker, creates isolated date-organized directories, and keeps started sessions resumable under Ungrouped.

224 days agoSessions & MessagesMIT
T

dsh-plugin-codegraph-project

troytse/dsh-plugin-codegraph-project

A CodeGraph tool scoped to the session's own indexed project, resolved from its workspace directory. One MCP server is launched through npx per project root and shared by every session working there; a project indexed mid-session is enabled without a restart, and the managed child process is reaped when the harness exits.

2last monthTools & CapabilitiesMIT
N

gord-dsh-worktree

nightosong/gord-dsh-worktree

Git worktrees for DeepSeek Harness — isolate parallel work in its own directory and branch. Ships Fast mode (快速模式).

210 days agoGit & Code ReviewMIT
M

dsh-session-eater

mikugui/dsh-session-eater

Session cleanup for the DSH sidebar: drag a conversation row onto the balance widget's whale and it eats the row — the session directory goes to a recycle bin, not to rm. Deletion asks one short question first (how many tokens it burned, and that prompt can be turned off in Settings). Undo from the persistent toast or the 12-entry log in Settings. Clicking the whale jumps straight to the plugin's Settings, where you can swap the avatar, drag the mouth into place and rewrite all 17 UI strings; blank, currently-open and running sessions are refused in place with a reason.

2last monthSessions & MessagesMIT
L

dsh-effort-ultra

loveirishcoffee/dsh-effort-ultra

A native reasoning-effort control for the composer: a blue-to-violet tier bar with a starfield and a sheen sweep. It owns the model seat and drives the official model-directories service, so the ladder comes from each model's own reasoning declaration and no other plugin is required.

22 months agoUI EnhancementsMIT
G

dsh-skill-authoring

gezi-wen/dsh-skill-authoring

Ships a skill about writing DSH skills - SKILL.md frontmatter and root precedence, how to phrase a description so it actually triggers, length and splitting rules, and an A/B check that the finished skill changes agent behaviour. The package also carries the checker the skill uses to validate a skill directory.

22 months agoSkillsMIT