Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

117 plugins found

X

dsh-privacy-gateway

xbzbing/dsh-privacy-gateway

Redacts secrets, cookies and personal data in every model request at the host process undici dispatcher and restores the placeholders in the reply, so one interception covers every provider, adapters that plugins add included; per-kind actions mask / warn / block, an optional same-shape fake key, records written to disk by the day and a statistics card.

37 days agoSecurity & PermissionsMIT
M

dsh-eda-mcp

mcviseron/dsh-eda-mcp

DeepSeek Harness (DSH) plugin — connects DSH to JLCEDA Pro (EasyEDA Pro) via a local MCP bridge and draws schematics through the JLCEDA extension API.

317 days agoMCP & ConnectorsApache-2.0
H

dsh-fight-scene-director

hatsuyuki0103/dsh-fight-scene-director

Registers the fight-scene-director skill for designing AI-video fight scenes, ported from the Codex skill of the same name. Emits structured Chinese prompts for Seedance 2.0/2.5 and MiniMax H3, plus trajectory-map and initial-position image prompts.

32 months agoSkillsMIT
J

dsh-secret-scrub

jkt-check/dsh-secret-scrub

Irreversible secret-scrubbing guard: rewrites access keys, bearer tokens, and private key blocks into `[REDACTED:<category>]` placeholders before they reach the session log and the model.

3last monthSecurity & PermissionsMIT
Y

dsh-home-migrate

ygcdsj/dsh-home-migrate

Export and import DeepSeek Harness configuration across machines as same-OS .dshmig archives, with credential redaction, verification and rollback.

33 months agoWorkflow & AutomationMIT
M

xiaofeiyu-academy

magicsandbag/xiaofeiyu-academy

Undersea learning platform for primary-school kids (grades 1-6): grade-based math/Chinese/English quizzes, a textbook shelf with PDF table-of-contents import, photo mistake collection, variant-question mastery tracking, a feedable fish pet with hunger, coins, outfits and achievements, multi-child profiles and progress reports.

26 days agoJust for Fun
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.

23 days agoModels & ProvidersMIT
R

cece_legal_skills

rainbowzhu22-eng/cece_legal_skills

A DeepSeek Harness bundle adapted from whatcccup/cece_legal_skills (MIT) for local DOCX, PDF, TXT and Markdown redaction with human review, PDF masking, local history and optional Agent rule edits. Requires Python 3.9+ and first-run dependency downloads. Model access is needed only for rule generation; 1.3.0 is a development prerelease and Windows acceptance is pending. The upstream is a standalone offline tool/SkillHub skill, not a DSH plugin, so it cannot be installed alongside this bundle.

214 days agoWorkflow & AutomationMIT
I

dsh-approval-gate

iamnewhands/dsh-approval-gate

Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.

220 days agoSecurity & PermissionsMIT
C

dsh-newapi-video

chen704290901chen/dsh-newapi-video

Call a new-api (one-api style) relay station's video model from the conversation with @-referenced image/video materials, supporting Seedance 2.0 and Happyhorse text-to-video and image-to-video across four relay protocols.

22 months agoModels & Providers
Z

dsh-postmortem

zzh-newlearner/dsh-postmortem

Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.

23 months agoDev & Plugin ToolsMIT
W

dsh-voice-agent (voice-app)

wayneyu430/dsh-voice-agent

A conversational voice frontend Agent for dsh: speak naturally over ByteDance Duplex, delegate requests to background tasks, and hear their asynchronous results reported by voice.

23 months agoVision, Voice & Multimodal
J

session-export

johnxu22786/session-export

Session export and compliance archiving for DeepSeek Harness: deterministic redaction, Markdown/JSONL/PDF outputs, on-disk archive management, and a trend/audit view.

23 months agoDev & Plugin ToolsMIT
X

dsh-showreel

xiaoyuer3921/dsh-showreel

Turns the latest completed DSH session turn into a shareable vertical recap video: editable five-scene storyboard, host-side privacy redaction, optional AI polish and TTS narration, MP4/WebM export with PNG cover.

23 months agoUI EnhancementsMIT
B

dsh-cyber-pet

borisshaw6/dsh-cyber-pet

Cyber whale pet for DeepSeek Harness: a floating, feedable, color-customizable whale over shell.overlay that reports token usage, quota, interactions, and session counts — one dsh-plugin bundle carrying the host chat brain and the browser surface

23 months agoJust for FunMIT
0

dsh-telemetry-redactor

030611/dsh-telemetry-redactor

Redacts supported secret patterns from the `session-telemetry/record` export copy before configured telemetry backends receive it.

23 months agoSecurity & PermissionsMIT
M

dsh-getnote

magicbaobaoli/dsh-getnote

A local-first Markdown panel for a 得到大脑 / Get笔记 vault: folder tree, tag cloud, full-text search, and a renderer for tables, timelines, Obsidian wikilinks and image attachments. Recording notes get an audio player with drag seeking and a timestamped transcript. Notes are plain .md files on disk, so a synced vault stays readable offline; cloud sync is optional, and deleted notes go to a restorable trash. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

12 days agoTools & CapabilitiesMIT
M

dsh-video-prompt

mujizi/dsh-video-prompt

Chinese video-prompt reference library with an interactive graph, timeline, topic wiki, and agent tools for browsing and retrieving attributed Wan3 examples.

15 days agoVision, Voice & MultimodalMIT
X

dsh-apikeys

xrc111/dsh-apikeys

A credential proxy for outbound API calls: keeps keys for GitHub, Cloudflare, Vercel, npm, Docker Hub, Hugging Face and custom platforms, and calls them from the Host so the model never holds the key. apikey_call takes a path rather than a URL, pinning the host to the platform definition; apikey_platforms lists accounts without values; apikey_key gets, sets or clears one; apikey_upload sends multipart with a file read from disk, bounded by an allowlist. Supports five auth shapes (bearer, custom header, x-api-key, basic, query string). Optional layers, each off by default or preserving existing behaviour: an AES-256-GCM vault with a scrypt-derived key and an authenticated header, a SHA-256 hash chain over credential operations that records no key values, response redaction of the key actually used, and per-platform failover on 401/403/429. Ships a CLI (list, verify, audit, call) that reads the same vault without the harness. By default (exposeKeys on) the apikey_key tool can return a stored key's value to the model, which puts it in the session log; turn exposeKeys off to keep keys inside the Host.

14 days agoTools & CapabilitiesMIT
H

dsh-tiedan-update

hochan666/dsh-tiedan-update

Adds two rows to the DSH general settings section. Version update asks the npm registry for a newer @deepseek-ai/dsh, installs it as a background job and streams the install output into the row; restart DSH stops the running process so its supervisor can start a fresh one. A second restart request is refused, and a systemd unit that reports no main process is refused rather than respawned beside it. The row also reports the process uptime and identity, so a page reconnect can be told apart from a real restart.

18 days agoDev & Plugin Tools
T

dsh-provider-doctor

tangyixiao/dsh-provider-doctor

Read-only diagnosis for a model provider that stopped working. Walks the connection chain one link at a time — host runtime and profile identity, the plugin row, whether the provider route is registered, whether it is configurable, the credential metadata the provider itself reports, the model catalogue, the provider's own diagnostic and the last recorded request — and labels each link observed, inferred or unavailable rather than guessing. Diagnoses the `workbuddy`, `workbuddy-ai` and `zcode-cli` routes from their plugins' public diagnostic commands, and adds a sidebar panel plus a copyable redacted report. The offline pass sends no model request, starts no process and reads no credential file; the connection check is a separate opt-in the panel describes before running it.

13 days agoDev & Plugin ToolsMIT
L

dsh-aidrama

limomss-dunang/dsh-aidrama

Pre-production studio for AI short dramas: imports a TXT/Markdown/DOCX script or pasted text, splits it into episodes, structures the bible, characters, scenes, props, episodes, shots and prompts, compiles prompts for the selected video-model dialect (Seedance 2.0/2.5, MiniMax H3, Kling, Wan), and hard-validates IDs, beat durations, dialogue capacity and look/identity locks before generation, and warns when a shot looks like it has more than one action.

111 days agoWorkflow & AutomationApache-2.0
2

dsh-go-local-voice

27synthesis/dsh-go-local-voice

Text-to-speech for the dsh-go native phone UI: long-press an assistant reply to read it aloud through Xiaomi MiMo TTS or ByteDance Doubao Seed TTS. The reply is segmented and pre-synthesized in the background after each turn, so one tap hands the app a single continuous MP3 instead of one short chunk per tap; playback has a stable lease so stop works, a status strip and progress bar give live feedback, and audio can be exported to phone storage. Keys stay on the device (0600) and are never rendered, committed, or sent to the model.

113 days agoVision, Voice & MultimodalMIT
L

DSH-Mem0

light-cheng/dsh-mem0

Mem0-backed long-term memory for DeepSeek Harness with managed Platform, self-hosted server and local OSS backends; visual settings, automatic recall (from the first turn) and capture, editable memory summary, token budgets and weekly memory hygiene that only deletes memories this plugin wrote. Captured text is redacted; the memory summary is a stable system-prompt section (plugin:dsh-mem0:profile) and recall a separate mem0:recall block appended last, so the cached prompt prefix stays stable; recall and capture have timeouts (recallTimeoutMs, addTimeoutMs). With dsh-strata installed, recall size follows its strataBudget allowance, and the optional captureStrataFolds setting (off by default) also saves its fold summaries as memories.

14 days agoMemoryMIT