Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

248 plugins found

J

dsh-token-panel

juhe291/dsh-token-panel

A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘:实时看会话压力、按模型估算花费。预算和余额点一下就能改,每天每月用了多少都有记录。

43 months agoUsage & BillingMIT
K

dsh-mistral-vibe-provider

khuraie/dsh-mistral-vibe-provider

Mistral Vibe Code as a DSH provider route — PKCE browser sign-in, the live model catalogue with per-model prices, the Vibe Code and Studio/API budget meters in Settings and the sidebar, and a per-session cost figure in the composer.

33 days agoModels & ProvidersMIT
F

dsh-qwen-token-plan-full

fushena/dsh-qwen-token-plan-full

Unofficial Qwen Token Plan provider: registers a `qwen-token-plan-full` route with a model catalog fetched from the gateway, Responses and Chat Completions protocols, server-side built-in tools, image and video generation tools, and per-entitlement budget tracking that disables a benefit once its quota is exhausted.

32 days agoModels & ProvidersMIT
G

dsh-auth-cookie-sweep

guyou9799/dsh-auth-cookie-sweep

Serves a live /auth-cookie-sweep page showing how full the local Host's cookie jar is, how many random-port launches are left before the 431, and repairs the jar in one click, while stale dsh-auth-* cookies expire automatically and the rescue budget grows to four times the largest jar seen, with no ceiling; DSH 0.2.2-rc.2/rc.3 fixed only the desktop shell, so browser jars and older releases still accumulate.

36 days agoSecurity & PermissionsMIT
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.

33 days agoModels & ProvidersMIT
3

dsh-cookie-guard

3150481853/dsh-cookie-guard

Windows-only. Counts the dsh-auth-* login cookies the DSH desktop shell has accumulated, shows how much of the 16 KiB request-header budget they eat and how many launches are left before the shell stops opening with "desktop welcome: Web authentication failed". The web UI gets a draggable floating card that re-checks every 10 minutes, keeps one snapshot per local date and can refresh on demand; a standalone Windows checker ships in desktop/.

322 days agoUsage & BillingMIT
J

dsh-context-budget

jidekaixin2dian/dsh-context-budget

Manage MCP servers and skills in DeepSeek Harness, and hide tool groups from the next prompt with token-cost estimates.

32 days agoTools & CapabilitiesMIT
T

dsh-workbuddy-connect-community

tangyixiao/dsh-workbuddy-connect-community

Community-maintained WorkBuddy and WorkBuddy AI model provider using local desktop sign-in, with model discovery and credit display. Version 0.1.23 retains saved-account credit refresh, check-in observations, and bounded 1/7/30-day statistics for text usage observed by this plugin; it refreshes exact-account context-window choices while retaining the CLI model roster and input/output budget, with one bounded supplementary CN read for missing tiers; it supports per-model context-window selection and DSH 0.2.1-rc.2, rc.3, rc.5 and 0.2.2-rc.1/rc.3; its CN compatibility layer differs from the functy23 fork. Derived from corrinehu/dsh-workbuddy-connect (MIT), it registers the same workbuddy / workbuddy-ai provider ids, so it cannot be enabled together with the original or other WorkBuddy bridges. Version 0.1.23 explicitly applies the synchronous Host request policy and authenticated owner admission to all nine registered HTTP routes, including update metadata, before body reads or route actions; missing, throwing, malformed or asynchronous admission services fail closed. Version 0.1.25 has been verified with DSH 0.2.2-rc.5.

319 hours agoModels & ProvidersMIT
X

dsh-user-memory

xinzeqing/dsh-user-memory

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

38 days agoMemoryMIT
W

EVA-Inspired-Theme

whatcannotbesaid/eva-inspired-theme

A Neon Genesis Evangelion-inspired skin for DeepSeek Harness: Title Card (light) and Central Dogma (dark) modes over one removable override layer, 55 measured color tokens, a wallpaper paint layer whose two surface alphas are solved against a WCAG contrast budget, a boot mask and a brand mark. It also rewrites the sidebar identity line, replaces the new-session heading, hides six official entries, and reshapes the composer control row. Unofficial fan work, non-commercial: the background pictures are fetched from third-party URLs at paint time, not shipped in the repository.

324 days agoThemes & Appearance
S

dsh-thincoder-suite

shenhuanageshei/dsh-thincoder-suite

Advisor reviews that converge over rounds, an engineering mode whose writes require a design token, escalation of a task to a stronger model, and parallel multi-model consultation; a settings page edits the model routes, timeouts and budgets.

3yesterdayWorkflow & AutomationMIT
B

dsh-agent-instructions

bay-zeddie/dsh-agent-instructions

Panel to edit dsh's native AGENTS.md from the web settings page: every layer in the instruction chain is clickable, three activation scopes, and a visual budget meter.

37 days agoIntegrations & RemoteMIT
D

dsh-pre-duediligence

duhu2000/dsh-pre-duediligence

Pre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.

32 months agoWorkflow & AutomationMIT
S

dsh-auto-compact

songoao25/dsh-auto-compact

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

33 months agoMemoryMIT
Y

dsh-plugin-cost-tracker

yytbit/dsh-plugin-cost-tracker

Token cost tracker for DeepSeek Harness -- track usage, calculate costs, budget warnings

33 months agoUsage & BillingMIT
D

dsh-novel-fade

drizzlegig/dsh-novel-fade

Writing a novel of hundreds of thousands, even millions, of words with AI — but always worried it will forget earlier plot, characters and foreshadowing? Loading piles of old chapters into the context every time is not only costly; it also crowds out the room that should go to actual creation. Fade gives the AI a long-form memory that gradually fades: the recent plot stays sharp, the distant story keeps its key points, and important characters and events can be recalled whenever needed. When a chapter is finished, its memory is organized and its text archived automatically — no need to carry the whole novel around. Cut unnecessary token consumption, keep more context and budget for the chapters ahead, and let AI help you write a longer story.

24 days agoMemoryMIT
I

dsh-injection-manager

iwhbiwhb/dsh-injection-manager

Sees and switches everything a new DSH session injects before its first request, with a content browser, cross-session injection trend, event log, health checks, presets and a token budget.

23 days agoUsage & BillingMIT
S

dsh-imperial-court

shilaoban666/dsh-imperial-court

Implements DeepSeek Harness's super-agent (router–worker) design on your own machine: a resident router, the Chancellor's Office, splits a request into tasks, triages and queues them by fixed rules without model calls, and starts each one as an isolated worker on its own git worktree and branch, surfacing only what needs your decision; an unattended mode repairs failed audits and archives passed ones. Inside each task the coding CLIs run as a Tang-dynasty court: one tool drafts a plan, a second reviews or vetoes it, six ministries work in parallel by dependency, an inspector checks each output and a final audit runs before you approve, and nothing is merged until then. Supports Claude Code, Codex, Gemini CLI, Cursor CLI, OpenCode, Qwen Code, WorkBuddy and DSH itself via dsh headless, with a tool catalog that shows install commands, per-call token and cost accounting with budgets, and an English Roman Senate mode.

26 days agoWorkflow & AutomationMIT
E

LMTAgent

eccvik/lmtagent

Multi-agent full-stack dev workbench for DSH (dsh-lmtagent v1.1.0): turns feature wishes into parallel file-disjoint coding shards with 8 role presets, detached standalone OS window, 1-click Git scope rollback, budget guard, and a live bilingual DAG console.

2yesterdayWorkflow & AutomationMIT
S

dsh-agents-md

sillykjs/dsh-agents-md

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

216 days agoUI EnhancementsMIT
K

dsh-fofatoto

keyblues/dsh-fofatoto

FOFA cyberspace mapping inside the conversation: check the account quota, run FOFA queries and export the full result set into CSV/JSON/TXT files in the session workspace by paging through a time cursor. A CSV or TXT export stopped by its time budget or by an upstream error continues into the same file from the saved cursor, so rows already fetched are kept. Results render as conversation cards (query, match count, file path), and the API key is saved from the plugin page into the Harness credential store.

217 days agoSecurity & PermissionsGPL-3.0
X

dsh-soul-evolve

xiachuyoufeng/dsh-soul-evolve

Persona state and slow evolution for DSH: five state dimensions (valence, arousal, energy, intimacy, focus) move after each turn and decay toward baseline over time; four scene types (work, tech, support, chat) modulate reply length and warmth without changing the state itself; the Soul panel keeps a persona card plus weighted evolution entries and injects them into the system prompt persona-first under a 4000-character budget. Ships a browser panel with a persona card editor and a live state view (the five metrics plus the last six events), appends a JSONL trace to disk, and seeds a usable default persona on first install.

216 days agoIntegrations & RemoteMIT
H

claude-on-dsh

huajikano/claude-on-dsh

Runs a project's Claude Code opening questions and plan, hands the task to DSH, and offers post-turn Claude review choices. Windows only, and requires a locally installed Claude Code CLI (set claudeCliPath if it is not auto-detected). New sessions handed to DSH are switched to danger-full-access. The first Claude run in a project folder sets hasTrustDialogAccepted for it in ~/.claude.json, and optional automatic Claude review is capped by a daily budget ($5 by default).

2yesterdayWorkflow & Automation
J

dsh-step-governor

jiewiw/dsh-step-governor

Deterministic step governance for DSH agents: rejects over-budget agent steps and denies risky tool executions before they run, with shadow mode by default and fail-open on errors.

217 hours agoWorkflow & AutomationMIT