Plugins
Browse, filter, and install DeepSeek-Harness plugins.
561 plugins found
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.
dsh-doctor (plugin)
moonquake2004/dsh-doctor
Offline diagnostic for DSH: 19 checks across env, profile, and session state, with a settings "Doctor" panel and a read-only JSON API.
dsh-remote-access-web (remote-access-web)
wikkd/dsh-remote-access-web
Reverse tunnel for the DSH Web GUI: exposes a `dsh --profile web` deployment at a public frp URL and switches the directory picker to the in-app browser, so a phone or remote machine can open and manage the workspace.
dsh-novel-voice
drizzlegig/dsh-novel-voice
Want AI to write in the style of novels you love, or to develop a voice that is uniquely yours? Creative Style imports novels you like and your own original work, distils their writing patterns into a personal style profile, and lets you blend several sources into one voice. Before you write it compiles a short brief; afterwards it points out clichés, repetition and off-style sentences, and can rewrite specific spans. Off by default, no scores, no model training.
dsh-algorithm-tools
springrinbowcat/dsh-algorithm-tools
Training workbench for competitive programming — syncs Codeforces and AtCoder submissions, profiles weak tags, picks a daily three-band problem set, reviews contests, and keeps a check-in calendar. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
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.
dsh-remedy (plugin)
jjjjjjjjnnjnn/dsh-remedy
A patch set for DeepSeek Harness that repairs fused tool-call argument text at the llm/stream seam and re-throws whatever it cannot prove: a call is dispatched only when every fragment parses to a plain object, the first call keeps its id and synthesized ones are marked, and a stream that cannot be split keeps its original error instead of a success. It also listens on agent/request-error to name the deterministic refusals it will not retry, answers per failure class which patch covers it and whether that patch is switched on in the profile you point it at, and reads multi-frame zstd session logs offline to count every turn ending and every error code. Everything it claims is registered with the seam it touches and the limits it does not cross; the resolver never invents a value and never downgrades a configured setting.
dsh-gatekeeper
huajikano/dsh-gatekeeper
Inspects the model's streamed reply before it is committed and either discards it or holds it for review when it reads as a refusal, so that text does not stay in the session context. Detection combines built-in phrase rules (an opening refusal, a capability denial, policy wording, first-person intent, refusals quoted in reasoning) with a plain-text word list and optional regular expressions. Interception can sit at the llm/stream waterfall, at the HTTP fetch layer before encryption (not TLS decryption, and it cannot tell which session a call belongs to), at both, or in a preview mode that shows a transient preview while the original chunks stay in memory until the whole reply has been checked. The same plugin also guards tool calls on tools/pre-execute: a command that deletes a drive, filesystem or user-profile root, formats or repartitions a volume, empties the Recycle Bin, fetches and executes a remote script, or writes to a raw device is denied, and a recursive delete outside build directories is recorded by default. Each tier can be set to deny, ask, record, or off, and the disk guard has its own switch. Both halves are heuristics: they can miss phrasings, the disk guard sees the arguments of a call rather than what a running script does, and they fail open.
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-rescue-guard
1250589385/dsh-rescue-guard
Standalone rescue for a broken DeepSeek Harness profile: a CLI that runs without DSH diagnoses the crash logs (six classified causes, from real incidents), pre-flights the profile for command-name collisions and files plugins read at construction time, arms a safe mode that loads only official bundles until a healthy boot restores them, and keeps manifest snapshots for rollback. A resident watcher watches the crash-log directories via OS file events — idle costs nothing, and when the loader dies the report is written within seconds, one file overwritten per crash. Windows only: crash logs are read from %APPDATA% and the watcher autostarts from the Windows Startup folder.
dsh-smooth
ayuanxx-max/dsh-smooth
DSH SMOOTH: config-only bundle for a lighter DSH UI - compact transcript and usage views, 16 px font and 200 ms job polling out of the box - plus a troubleshooting SKILL.md and opt-in recipes (appended by hand to your own cordis.patch.yml or the profile) to remove the Agents-Anywhere "Reconnect" button, slim the tool list, drop legacy sub-agent bundles and make compaction thresholds take effect. User patches still win; rollback = remove the bundle.
dsh-shortcuts-prompt
smithtomge-alt/dsh-shortcuts-prompt
Adds a strip of saved prompts above the composer: click a chip to insert its text at the draft caret, and manage the list — add, edit, reorder, delete — in an inline panel that opens in place. Prompts persist per profile and are also exposed to the agent as a quick_prompts tool; a fresh install starts with no entries.
dsh-groups
zyfsyx666/dsh-groups
Group installed DSH plugins into named sets and enable, disable or exclusively apply them by rewriting the profile bundle list. Can also render a set as an agent preset that a single conversation uses.
agentkit-personal-assistant
kingsoftcloud/agentkit-personal-assistant
Standalone personal assistant DSH plugin with multi-Bot profiles and an explicit Cloud Computer Broker boundary.
dsh-cap-manager
easun-zhu/dsh-cap-manager
One panel for MCP servers, skills and Claude Code plugins across global/profile/project scopes: live status, import/export, trash & backups, and the official claude-plugins-official market (install/update/uninstall).
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-lab-assistant
oddeye4649/dsh-lab-assistant
Desktop-pet lab assistant for DSH that keeps experiment records, accumulates per-software notes, and generates Word/Markdown lab reports from real step-by-step evidence. The desktop pet and lab panel require the Windows desktop build of DSH; other profiles get the conversational tools only.
dsh-prompt-manager
elfmingh/dsh-prompt-manager
Layered system-prompt profiles — global, per-workspace and per-session entries injected in order — where individual builtin sections and runtime contexts can be disabled or overridden, with a line-level diff of what an override changed; each entry carries a subagent scope that targets the main agent only, subagents only, or both; assembly snapshots record what each turn actually received, subagents included. Managed from a Web panel and a `prompt_manager` tool.
dsh-sync
shangshuo/dsh-sync
Encrypted, scheduled backup and restore of a DSH profile — plugins, settings, skills, UI preferences and optional MCP connector or API keys — to S3-compatible storage, WebDAV or a local folder.
dsh-subagent-models
garybot126/dsh-subagent-models
Set the provider, model and reasoning effort delegated subagents run with, from one chip beside the composer: a per-conversation override and a profile-wide default share the same two controls, and the chip always shows the effective route. Applied when each in-process child is created (agent/created + agent.model.select()); no settings page, no preset edits, no model-facing tool parameters.
dsh-assistant-profile
istarrydust/dsh-assistant-profile
Agent persona: gives DSH one global persona (name, language, persona prompt) that every new session carries at the front of its system prompt, plus a long-term memory you grow from any chat in one click; three built-in presets ship with it, and a Big fat fish persona is active right after install; chat sessions can also be deleted from the sidebar row menu.
dsh-image-hub
tianfangliu98-cpu/dsh-image-hub
Image generation through eight provider APIs (Labnana, OpenAI, Gemini, Seedream, DashScope, xAI, Zhipu, ComfyUI) with multiple saved profiles, a per-conversation gallery, and credit tracking on Labnana.
dsh-pouch (dsh-mcp-console)
moon16u/dsh-pouch
MCP server console under Plugins: manage the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/delete servers, enable/disable/reconnect, per-tool switches, live status and tool lists over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries; an uninstall leaves a native fallback block that keeps the same servers loadable.
dsh-token-frugal
xuzihao66/dsh-token-frugal
Cuts session input tokens three ways, each with its own switch in a panel under the composer: lossless structure-aware compression of tool results on `tools/post-execute`, then a per-tool head/tail elision that always names a recovery path through the shared spill store; tool-catalogue visibility per agent on `agent/created`; and a per-workspace memory document that recall matches against each new message and injects through `agent.inject`, so the transcript is not re-read. Measured 41.76% fewer prompt tokens over 149 recorded requests, with a bundled script that re-measures any profile.