Plugins
Browse, filter, and install DeepSeek-Harness plugins.
399 plugins found
dsh-plugin-weaknet-adaptor
jiay98528-dev/dsh-plugin-weaknet-adaptor
Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.
dsh-usage-monitor
noirbright/dsh-usage-monitor
Settings usage dashboard: tokens, requests, output tokens, and cache-hit rate from session logs, with a stacked chart and a breakdown table by provider, model, or workspace.
dsh-deepseek-usage-dashboard
izz-blue/dsh-deepseek-usage-dashboard
DeepSeek API usage dashboard for DSH Web: daily cache-hit/miss and output token statistics from session logs, per-model cost estimates, account balance, 7-day trends, and a composer usage summary.
dsh-usage-dashboard-plus
1helloman1/dsh-usage-dashboard-plus
Shows DeepSeek balance and estimated daily spend, merges external vision-call JSONL records, and adds a per-session dashboard with model statistics, TTFT, cache rate, call logs, cost estimates, filters, and CSV export.
dsh-llm-vision-bridge
einskyle/dsh-llm-vision-bridge
Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
dsh-locator
perrylink/dsh-locator
Whole-disk file-name search for DSH with a self-built cross-platform index, agent tools and a Web panel; no Everything required. It indexes your home directory by default; the first content search also builds a local full-text index (SQLite in the platform cache directory) of text and source files there (by extension, up to 1 MB each, 200,000 files) and of your recent DSH session messages; locator_export writes a SQLite copy of the index to any absolute path it is given, replacing an existing file when overwrite is true. The engine is a prebuilt Go binary shipped for six platforms (source in engine/), and the plugin makes no network requests.
dsh-code-explainer
xiaoluoli45/dsh-code-explainer
Adds a Chinese end-of-line comment to every line of code shown in a DSH tool card - grey for the call being made, blue arrows for code in the output - written instantly by a local rule set and, for lines the rules cannot judge, by the current session model; a header toggle returns the block to plain code, and credentials are masked before anything is sent or cached.
dsh-github-radar
goodboys155/dsh-github-radar
Right-sidebar GitHub panel with four rising-repository lists — created within 2 days, 7 days, 30 days, and 20k+ stars still pushed — where the first three are ranked by star velocity (stars per day) rather than total stars, so repositories that gained traction fast surface above older ones with more stars. Each row shows the repository name, its own description, language, the stars-per-day rate and up to two topics, and links to the repository. A keyword search box queries the GitHub Search API directly, debounced and IME-aware so a Chinese or Japanese composition costs one request instead of one per keystroke. Reads the public GitHub Search API anonymously: no token, no login, no account, nothing else contacted. Lists cache for 30 minutes and search results for 5; outbound requests go direct first and fall back to a listening local proxy port only if direct fails.
dsh-session-recycler
zhezhi33/dsh-session-recycler
Two-stage session deletion for DSH on Windows: move a conversation to the recycle bin and restore it to its original sidebar slot; deletion confirmed in two steps to prevent deleting files by mistake, clearing the whole subagent tree, sidebar ledger, projection cache, log lines and exclusive attachments along the way. It also scans the files a conversation actually wrote, adds a file query that pastes the path information into the conversation so an agent can judge which files are safe to delete, highlights them in Explorer, and copies the paths grouped by type. Both this and iamwuzhanglin/dsh-session-recycler install under the package name dsh-session-recycler, so install only one of them.
deepclean-mydisk-plugin
huangxiaoliang/deepclean-mydisk-plugin
Disk cleanup for Mac (macOS) and Windows: a risk-tier audit and space breakdown, then moves caches, leftovers and similar photos to the Trash or a quarantine folder, with undo. Space is freed only after a batch is permanently deleted.
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-tide-theme
zdt3476/dsh-tide-theme
Deep-sea tidal-blue theme for the DeepSeek Harness Web client with a single accent color and matte (non-glass) surfaces in light and dark modes. Same-token UI additions: a single-line dock HUD reading real session projections (context usage vs. window, TPS, cache-hit rate, elapsed time), per-turn subagent delegation cards showing token usage and an optional cost estimate from OpenRouter public prices, sidebar pagination with pinned sections and type-to-filter, and model / reasoning-effort / permission controls under the composer. Each addition can be toggled in the plugin settings.
dsh-token-gauge
liumiaozhi/dsh-token-gauge
Sidebar token gauge for DeepSeek Harness: live output-speed dial, current-session and today token totals, estimated spend from DeepSeek list prices with half price off-peak, and a 70-100% cache-hit dial, with single- and dual-gauge layouts and four skins.
dsh-context-compaction-optimizer
bigpaulsixsixsix/dsh-context-compaction-optimizer
DSH plugin: mark messages as invalid so an operator annotation digest steers what a compaction checkpoint absorbs. Cache-preserving: appends after the cached prefix, never rewrites history.
dsh-disk-janitor
algorandius/dsh-disk-janitor
Disk Janitor for DeepSeek Harness — reports where DSH disk usage goes and reclaims only what is safe to rebuild, always keeping the resources currently in use.
dsh-manage-session
drscrewdriver/dsh-manage-session
Session Manager for DSH (formerly Session Steward): one console over active and archived sessions — grouped by workspace, domain and title filters, favorites, and batch archive / unarchive / purge archived files (destructive steps ask twice) — plus a four-gate health checkup (log integrity, projection cache, lossless JSON, cold read) that ends in a reversible, backup-first prescription. Search and indexing live in dsh-search-index; this plugin builds no index and never rewrites session logs.
dsh-session-remove
bg0exm/dsh-session-remove
Stop or permanently delete DeepSeek Harness sessions from the sidebar session menu: cancels running turns, subagents, background jobs and reminders, then removes the log, subagent session logs, projection cache and workspace record, with an optional clean
dsh-context-reclaim
xiamubumu/dsh-context-reclaim
Context governance for DSH: folds oversized tool results, collapses the tool surface and keeps the prompt cache warm, so long sessions stop getting more expensive.
dsh-token-saver
lovedolove/dsh-token-saver
DeepSeek Harness plugin that trims tool output (head/tail plus grep folding), adds optional prompt shaping (Caveman and Ponytail), instant local responses, RTK command-output compaction, context-pressure handling, optional LLM-summary compaction, stable prompt-cache layout, a Web settings UI, and persisted savings telemetry.
dsh-token-total
gaohu1997/dsh-token-total
Token usage dashboard and per-session tree statistics: provides time-range filtering, 6 summary metric cards, GitHub-style activity heatmap, model stacked-bar charts with cache hit rate curves, and Top-5 model/provider rankings; enhances the native session status bar to display aggregated token usage across main agents and all subagents with detailed breakdowns.
dsh-session-purge
wwwyxsuper/dsh-session-purge
Adds a permanent-delete row to the sidebar menu of archived sessions, removing the session log, its projection cache and its workspace registration.
dsh-plugin-ide-hub
121212165/dsh-plugin-ide-hub
One hub over every coding IDE you run — dsh, Claude Code, Codex, ZCode, Qoder, CatPaw, Trae, OpenCode. Zero-API: it reads each tool's own on-disk state and gives a session inventory, per-IDE usage with cache-hit rates, one-line resume commands, and a single .hub/ rule body wired into all eight via marker-delimited pointer files. The domestic-IDE adapters (Trae/Qoder/CatPaw) were verified against the installed binaries — a gap no overseas tool covers.
dsh-context-governor
mpinaev/dsh-context-governor
Context fullness bands, the per-session compaction threshold derived from the model window, per-step cost computed from cache read and cache write rates, cache-hit, DeepSeek balance with the peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.
dsh-reply-visual
yfwu2020/dsh-reply-visual
Adds a diagram button under every finished reply in the DSH Web UI: the configured model writes a single-file HTML page with inline SVG and the right sidebar renders it in a sandboxed iframe, with diagram, source and original-text views, a per-session replay history that is served from a disk cache instead of calling the model again, redraw, and save to a .html file.