Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

37 plugins found

P

dsh-quant

pengpengyi92/dsh-quant

Quantitative R&D toolkit for DeepSeek Harness — 59 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk (VaR/CVaR/drawdown/Beta with Kupiec POF), options, bonds, FICC and fund simulation, with an end-to-end PDAT→PET research pipeline.

7317 hours agoTools & CapabilitiesMIT
X

OpenQuantum (openquantum-web-branding)

xi-zhao/openquantum

Applies OpenQuantum branding, browser metadata, and PWA assets to the native DeepSeek Harness web UI.

72yesterdayUI EnhancementsMIT
U

quantum-practices

unitarylab/quantum-practices

Quantum Algorithms Best Practices

173 months agoSkills
T

dsh-novel-solo

tkingxiao/dsh-novel-solo

"Single-Core Writing" plugin for DeepSeek Harness: Thoroughly tool-streamlined and output-hardened for quantized small models, suitable for running long-novel pipelines locally with on-device models.

1414 hours agoWorkflow & AutomationMIT
A

dsh-expert-mode

asher-2000/dsh-expert-mode

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

142 months agoTools & CapabilitiesMIT
W

stock-analysis-plugin

weaxs/stock-analysis-plugin

DeepSeek Harness (dsh) plugin for stock analysis, screening, and strategy backtesting across A/HK/US/JP/KR/TW markets

113 months agoTools & Capabilities
L

dsh-rigorquant

linxichen/dsh-rigorquant

RigorQuant preset + skill pack: unattended walled multi-agent research for empirical and computational mathematics (economics, finance, portfolio), with a four-part pre-implementation check battery and a jacobian/Lean escalation lane.

102 days agoSkillsMIT
X

dsh-plugin-stock-x

xuexiaolei1997/dsh-plugin-stock-x

Financial quantitative workbench and stock ticker: floating ball and drawer panel, real-time A/HK/US/global market quotes, multi-period K-lines and 5-day intraday charts, depth order book, capital flow, sector heat map, and AI investment research.

92 months agoUI EnhancementsMIT
K

bigA

kobenfang/biga

A-share stock analysis and screening skill: real-time quotes, technical timing scores, buy/sell signals and a managed watchlist.

93 months agoSkillsMIT
M

dsh-openrouter-providers

moranyue/dsh-openrouter-providers

Route OpenRouter requests through a configured provider list and quantization cap, injected as provider.only/order with allow_fallbacks, plus provider.quantizations.

75 days agoModels & ProvidersMIT
L

data-asset-inspector (data-asset-quality-score)

liuhange789/data-asset-inspector

Quantitative data quality scoring based on GB/T 36344-2018, providing auditable quality reports for data asset capitalization.

64 days agoTools & CapabilitiesMIT
I

dsh-plugin-mlquant-benchmark

initial-d/dsh-plugin-mlquant-benchmark

DSH tools for reproducing and validating the ml-quant-trading protocol v1 CPU benchmark, then drafting an issue-ready report. Requires a local clone of initial-d/ml-quant-trading (set as the workspace or repoPath) plus Python and PyTorch; this plugin does not fetch the repository or install its dependencies.

52 months agoTools & CapabilitiesMIT
P

dsh-bayes-predict

pg527322814/dsh-bayes-predict

Bayesian stock prediction plugin that fuses MACD, RSI, moving-average, volume and other technical signals into an up-move posterior probability with multi-horizon comparison, trend-state classification and position risk metrics for A-share and US stocks.

3last monthTools & CapabilitiesMIT
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.

22 days agoModels & ProvidersMIT
H

dsh-astock

hzy1522/dsh-astock

A股 / 港股量化工作台:自选股、K线图、公司数据、策略配置与回测。 · A-share & Hong Kong stock quant workbench for DeepSeek Harness.

22 months agoTools & CapabilitiesMIT
J

dsh-wakatime-plugin

julardepick/dsh-wakatime-plugin

A plugin for dsh: quantify every dsh Agent interaction as a visualized performance metric and automatically sync it to WakaTime, using data to showcase your productivity with Agent.

25 days agoTools & CapabilitiesApache-2.0
N

dsh-hhxg-market

niceck/dsh-hhxg-market

恢恢量化 (hhxg.top) A股量化数据插件 for DeepSeek Harness:13 个工具——日报快照 / 财经快讯 / 融资融券 / 投资者事件日历 / 市场情绪 / 题材热度 / 数据集目录 / 个股诊断 / 条件选股与策略预设 / 连板晋级预测 / 异动历史 / 数据集查询 / 盘中实时,全部经 hhxg MCP server 取数,填入 Max 会员的 AI 接入 Token(MCP Token)即用。A-share quant data plugin for DeepSeek Ha

19 days agoMCP & ConnectorsMIT
T

stockproof (dsh-plugin)

taoqizhang55-code/stockproof

Stock research tools for US, China A-share and Hong Kong stocks via the stockproof MCP server (Python 3.10+; install with pip install "stockproof\[mcp,cn]" — A-share/HK data needs Python 3.11+): news, earnings and announcement reads with cited sources, explanations of price moves, a whole-market A-share screen, a quant lab that backtests ideas on point-in-time history with a locked holdout, a portfolio check-up and a local web dashboard; 23 tools.

113 days agoTools & CapabilitiesMIT
P

dsh-ifc-qto

perrylink/dsh-ifc-qto

IFC model quantity take-off with CSV export for quantity checking.

16 days agoTools & CapabilitiesApache-2.0
B

dsh-plugin-baiguangda-style

browhitebyte/dsh-plugin-baiguangda-style

Chinese writing-register plugin for the Gcores/机核 editor 白广大: registers a 40 KB style skill plus style_lint / style_audit / style_rules tools — 4 hard-error and 27 warning checks (banned connectives, slogan inflation, empty quantifiers, uniform paragraphs, unsourced statistics, AI clichés), with thresholds calibrated on 444 articles / 802k characters; a settings page adds an on/off switch, single and batch trial runs, and JSON threshold overrides.

122 days agoTools & Capabilities
Y

dsh-jev-preset

yum-wu/dsh-jev-preset

JEV agent preset bundle with prompt-guided task routing, cross-verification and quantitative checklists.

1last monthWorkflow & AutomationMIT
P

dsh-hazchem-check

perrylink/dsh-hazchem-check

Checks a hazardous-chemical register for internal consistency: that each substance names its hazard class, that stored quantities parse, that a threshold is recorded, that the major-hazard-source verdict agrees with how the stored quantity compares to the threshold the register states, that safety data sheet numbers are present and CAS numbers are not duplicated. Reports differences for a human to review; it does not decide whether a unit constitutes a major hazard source.

19 days agoTools & CapabilitiesApache-2.0
G

dsh-plan-adversarial

gendui123/dsh-plan-adversarial

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

13 months agoSecurity & PermissionsMIT
Z

dsh-vertical-kit (dsh-weekly-report-check)

zjukop3/dsh-vertical-kit

Weekly-report hygiene from markdown: what was done separated from what is planned, risks and blockers named, and at least one quantified item so progress is tellable from motion. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

0yesterdayTools & CapabilitiesMIT