Plugins
Browse, filter, and install DeepSeek-Harness plugins.
400 plugins found
dsh-store
huguangyu666/dsh-store
Plugin store: npm authoritative catalog + awesome curated list (550+ plugins, 11 categories), dsh-field quality verification, official `dsh plugin add/remove` one-click install, sidebar + settings entry.
dsh-web-preview
zoumutou/dsh-web-preview
Side web-preview panel: local static hosting, Markdown/code/image preview, one-click run of non-static projects (Cargo/npm/Go/Python) with live logs, drag files into the chat (saved to the workspace), element mark & annotate, workspace file search on 404, and link-click takeover into the side panel.
dsh-enforce-package-manager
acus9345/dsh-enforce-package-manager
DeepSeek Harness plugin that catches the wrong package manager for the repo (npm install in a pnpm repo, pip install in a uv/poetry project, and so on) and gives the model the exact right command.
dsh-plugin-upgrader
zuwenyin/dsh-plugin-upgrader
A Versions tab on the Plugins page: one-click upgrades that replace the plugin in place where they can (no uninstall, enabled state preserved, falling back to remove + reinstall with the reason logged when the profile writer lock is busy), live pnpm output with per-step timing and cancel, the full published version history with one-click rollback, every version checked against the running DSH so incompatible ones are marked and blocked, a rollback that installs the old version but cannot activate it reported separately from a lost package, profile manifest writes taken under the harness writer lock with one recoverable journal record per package after a failed upgrade, mirror-gap warnings, and a selectable npm registry saved in the profile.
dsh-portable
wjf1/dsh-portable
Export a whole working DSH home — profile, installed plugins with their node_modules, skills, hooks and task boards — into one .dshpkg tar and import it on another machine without network or pnpm; also streams over HTTP or a one-shot LAN link.
cli-doctor
maxhou-infinity/cli-doctor
Read-only audit of the local CLI toolchain as a sidebar panel in the DSH web GUI: lists installed versions across Homebrew, npm global, pip, Rust/Bun/uv and self-updating CLIs, flags which ones have a newer release available, and shows the dependency impact for installed packages. It reports only and never runs an upgrade, so no tool on the machine is modified. The DSH plugin ships on npm as `dsh-cli-doctor`.
dsh-live-data
uckkk/dsh-live-data
Ten live-data tools over eight keyless public APIs: FX rates, weather, npm/PyPI versions, GitHub repo stats, Bilibili video stats, A-share/index/gold quotes, and IP geolocation. Tool defaults are configurable in settings.
dsh-versions
shangdi178/dsh-versions
Version manager for the dsh host in a settings section of its own: shows the installed version against npm dist-tags, checks for updates, and installs, upgrades, downgrades or reinstalls any published version with a pre-upgrade local snapshot, failure rollback, snapshot-based rollback and an upgrade history. Before a cross-minor install it compares the @deepseek-ai/dsh-settings exports of the target release with the named imports of installed plugins to flag those that would stop loading, and it can apply or remove reversible compat shims that port removed legacy APIs back into framework files. Upgrade, restore and restart engines are Windows-only; version listing and checks work on every platform.
dsh-plugin-mgr
oxlyn/dsh-plugin-mgr
Card-style plugin manager in Settings: enable/disable each plugin through the profile patch layer, install-source details, npm update check with one-click update, uninstall, search, and load-error badges.
dsh-liquid-glass-input
jkamkk/dsh-liquid-glass-input
Liquid Glass refraction input card for the DSH web GUI, with coupled-spring press animation. Published on npm: dsh plugin --profile web add dsh-liquid-glass-input.
dsh-native-session-manager
wsl043/dsh-native-session-manager
Manages archived DSH sessions in the native sidebar with conversation search, restore, and confirmed safe permanent deletion.
dsh-unified-market
jing-hy/dsh-unified-market
Unified plugin marketplace built for the DSH Desktop (EAC) shell, aggregating the curated catalog, the GitHub dsh-plugin ecosystem and the npm registry into one storefront, with source whitelisting, conflict pre-checks, trial-boot install verification, manual/batch/auto updates and .dshpack feature-pack management.
dsh-plugin-diraud
tttwh/dsh-plugin-diraud
Installed-plugin catalog for DSH: group plugins by origin (official vs self-installed) in a searchable panel with enable/disable, uninstall, and one-click update. Published on npm as dsh-plugin-diraud.
dsh-session-delete
wsl043/dsh-session-delete
Adds a red permanent-delete action with a confirmation dialog to the native session menu.
knowlp-rag
wly8691-jpg/knowlp-rag
Dual knowledge-graph RAG for Markdown notes with half-life memory decay: prerequisite + similarity graphs (P/S-Agent traversal), paragraph chunking, n-gram/embedding hybrid search, and an explicit weight-feedback loop — a native Cordis plugin, npm-installable as @eqman00003/knowlp-rag.
dsh-skill-panel
ztqing4agents/dsh-skill-panel
Panel for the DSH web GUI that keeps built-in, local and market-installed skills in one list, decides each row by on-disk evidence (symlink, install ledger) under a fixed precedence, listing a duplicated name once, from the higher-precedence source. Switches rewrite disable-model-invocation in its own SKILL.md; built-in skills have no writable file, so the panel stores their state and says the registry is unchanged; symlinks are read-only. The add dialog takes a local directory or a public github.com link (.git, /tree, #path:), shallow-cloned. A market tab browses the skillhub.cn mirror across three source scopes and installs into ~/.dsh/skills, with update checks and rollback on failure. UI ships in Chinese and English. Package name is @ztqing4agents/dsh-skill-panel (npm) and the mount id stays dsh-skill-panel, so it installs alongside dsh-skill-center. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-g-memory
gladess1102/dsh-g-memory
Cross-session semantic memory for DSH: indexes session history locally with EmbeddingGemma 2 embeddings and recalls relevant past context, injected as clearly-framed untrusted context. No npm runtime dependencies; synthesis is opt-in.
dsh-code-review
jkin8010/dsh-code-review
Code review center for DSH, built on open-code-review: reviews current changes, commits, branch ranges, project architecture, code modules and business data flows, with live progress, a GitHub-style commit heatmap, fixed markers, automatic fix verification, light/dark themes and one-click fix sessions. Needs git; AI review also needs the open-code-review CLI 1.13 or later (npm i -g @alibaba-group/open-code-review), and the reviewed code goes to that CLI's configured LLM, or to the session model when the review is delegated to it. The engine is picked automatically — that CLI's model, then the session model, then offline structural analysis — so findings still come back with no API key; reopening a report after a fix session re-runs the review to verify the fixes.
dsh-better-plugin-updater
mooling0602/dsh-better-plugin-updater
Update checker for plugin bundles installed in a DSH profile: a Version section on the detail page of a plugin installed from a GitHub repository or release tarball compares the installed commit or version with the exact target, and the /plugin-updater commands list bundles, check npm, Git-repository and GitHub-release sources, and prepare an update that runs only after confirmation; a read-only plugin_updates tool lets an agent check without installing, npm registry packages keep DSH native update controls, a fixed version or commit stays pinned unless explicitly allowed, and the plugin never approves build scripts.
dsh-hoi4-modding
kiant98/dsh-hoi4-modding
Hearts of Iron IV modding bundle for DeepSeek Harness: registers 15 skills covering focus trees, events, decisions, ideas, characters, technologies, localisation, GUI and error.log triage, and mounts 20 local MCP tools (a Python stdio server) to scaffold content, statically validate mods, build a SQLite FTS5 knowledge base from the vanilla game, and preview focus trees offline. Ships a 163-document reference library; requires DSH >=0.2.0 <0.3.0 and Python 3.9+ on PATH (standard library only, no game assets).
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.
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.
dsh-aide
prismscopes/dsh-aide
VS Code-style local IDE for DeepSeek Harness: Monaco editor, explorer, search, Git, terminal, and language services. With pnpm, run `pnpm approve-builds --all` so the native build of node-pty is allowed.
respire-dsh
risense-ai/respire-dsh
Respire memory for DeepSeek Harness (dsh). npm: @rsrsai/dsh