Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

166 plugins found

D

dsh-reference-session-collector

drscrewdriver/dsh-reference-session-collector

Read-only session-log projector (drsc) for DSH: scans ~/.dsh/sessions/**, decodes zstd/tiled-frame logs with a vendored leaf decoder and rewrites per-session projections into its own SQLite (node:sqlite, segments / replaces + FTS5), exposed through a single fenced HTTP route — surface ledger, recall/compression pair accounting and Chinese-capable full-text search. Token counts share the exact DeepSeek-V4 tokenizer and formula as CCI verify, falling back to a labelled chars/4 basis when assets are absent. Never writes session files; all output lands in its own data directory. Serves three consumer plugins: context-compression-improved (surface marking + recall reconciliation), session-steward (search-corpus switch), prime-memory (historical anchor backfill). Hosts 0.1.0-rc.2 .. 0.2.1-rc.2 (17-tag exact engines.dsh enum). npm: dsh-reference-session-collector.

4yesterdaySessions & Messages
X

dsh-goal-mode-enhance

xlennart/dsh-goal-mode-enhance

Visual goal lifecycle for the DSH web UI: a composer dock to create, multiline-edit, pause, resume, complete and clear session goals with live round progress, plus a phase-dot composer entry and a settings-page goal overview.

413 days agoUI EnhancementsMIT
Q

orbital-agents

qulierm/orbital-agents

Persistent Endeavour and Challenger peer sessions for DeepSeek Harness that plan, execute sequential tasks, and verify reported results.

4last monthMemoryMIT
L

dsh-attachment-formats

linkingoscar/dsh-attachment-formats

DeepSeek Harness Web plugin — PDF text-layer and scanned-PDF OCR, Office docx/xlsx/pptx to Markdown, TIFF/epub and long-document index cards.

42 months agoTools & CapabilitiesApache-2.0
Z

dsh-fix-duplicate-loader-id

zhao1012/dsh-fix-duplicate-loader-id

Diagnoses and fixes "duplicate loader entry id" boot crashes - finds duplicate loader rows across profile bundles and converts them into id-targeted patches via a zero-dependency CLI (detect / preview / fix / verify).

43 months agoSkillsMIT
M

dsh-scout

maxhou-infinity/dsh-scout

Evidence-driven company and job due-diligence for DSH: logs sources with evidence levels, adds evidence-bounded claims, verifies the legal entity against official registries, and renders a PROCEED/VERIFY/STOP report with a verification checklist and interview questions.

416 days agoTools & CapabilitiesMIT
H

dsh-better-tips

hakureimonika/dsh-better-tips

Recovers socket cause chains, key HTTP response headers, and size-limited error bodies from failed DSH model requests, shows them next to the native error, and adds bounded extra retries for model and compaction requests.

32 days agoDev & Plugin ToolsMIT
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.

36 days agoModels & ProvidersMIT
X

dsh-lead-mode

xiebaiyuan/dsh-lead-mode

Lead-mode agent preset plus two runtime skills for the official Agent Teams runtime: a delegate-wait-verify working method, and a wrap-up digest that merges several members' output into one file. Ships no team runtime of its own.

311 hours agoSkillsMIT
A

dsh-workplan

abbaababa/dsh-workplan

Durable task-decomposition plans for DeepSeek Harness with a self-learning loop: every department subtask runs in three ordered phases (plan, execute, verify), the verify phase must submit a retrospective of problems, detours and resolutions, and that retrospective is written to a permanent lessons file, ranked against the new subtask and injected into later dispatches so the same mistake is not repeated. Adds a read-only dsh_workplan_lessons tool (11 model tools in total), a progress panel drawn as a ring, a stacked bar and per-stage steps, and a public ISO/IEC 15408:2026 security self-assessment with zero runtime dependencies.

311 hours agoWorkflow & AutomationMIT
G

touchstone-dsh

gavinc-cn/touchstone-dsh

AI-agent-driven automated testing platform for DeepSeek Harness (dsh): drives the harness agent through long-lived multi-round sessions to write and run Markdown test cases, file bug reports, fix the code and re-verify the fix, with a per-project serial queue, a development board and built-in load testing.

312 days agoWorkflow & AutomationMIT
D

interest-memory

djasdh/interest-memory

Cross-session long-term memory backed by a local Go service (~50MB RAM, SQLite-vec + verify-augmented claims): zero-lag recall injection on every user message, session-end transcript ingest, and memory_search / memory_logs / memory_ingest tools. Install with `dsh plugin --profile web add @djasdh/interest-memory-dsh-bridge`. Protocol bridge only: the Go service is not installed by `dsh plugin add` — install and start it per the repository README first; until it runs, the tools silently return nothing.

33 months agoMemoryMIT
Q

dsh-hiboard-push

qinpanwan/dsh-hiboard-push

Huawei HarmonyOS assistant-today (负一屏) task-completion push for DeepSeek Harness: hiboard_push / hiboard_verify tools post Markdown task results to the phone card feed, wire-compatible with the OpenClaw today-task skill, with the authCode managed from the dsh settings panel.

33 months agoIntegrations & RemoteMIT
Y

dsh-opencode-free-models

yu-wenchao/dsh-opencode-free-models

OpenCode Zen 免费模型面板插件:实时展示 OpenCode Zen 最新免费模型,一键置入 DSH 模型选择器,无需密钥即用(共享字面量密钥由宿主注入)。后台支持总开关 / 单模型下架管理。

33 months agoModels & Providers
H

oh-my-dsh

hawk2048/oh-my-dsh

OMC-style multi-agent orchestration for DeepSeek Harness: 29 omd-* skills and 12 /omd-* slash commands over the plan-execute-review-verify pipeline and team/autopilot/ralph modes.

3yesterdayWorkflow & AutomationMIT
Y

dsh-tool-lipsync

yu-wenchao/dsh-tool-lipsync

Free lip-sync video generation plugin for DSH with 3000+ voices and 500+ languages.

33 months agoVision, Voice & MultimodalMIT
K

dsh-goal-mode-enhance

karloflaw/dsh-goal-mode-enhance

Visual goal lifecycle for the DSH web UI: a composer dock to create, multiline-edit, pause, resume, complete and clear session goals with live round progress, plus a phase-dot composer entry and a settings-page goal overview.

33 months agoUI EnhancementsMIT
X

math-research-dsh

xsoc1/math-research-dsh

Rigorous open mathematics research suite: four agent skills (rigorous-open-math-research, manage-math-research-program, math-research-workflow, lean-verify) for theorem solving with adversarial audit, research program management, pipeline orchestration, and Lean 4 formalization audit; CI-verified tests and mechanical upstream sync.

314 days agoSkillsMIT
B

dsh-plugin-anydoc

beancookie/dsh-plugin-anydoc

This plugin exports a reusable function that takes a file path or a Buffer, extracts the content via @firecrawl/anydoc, and returns GitHub‑Flavored Markdown (GFM). It also includes configuration options and an example usage.

33 months agoTools & Capabilities
K

dsh-skill-loader

kezboardpj/dsh-skill-loader

33 months agoSkillsMIT
L

dsh-paper-translate

linlinxxy77-hue/dsh-paper-translate

Translates English academic-paper PDFs into Chinese DOCX while preserving the original layout (figures, captions, three-line tables, formulas, and reference positions unchanged; reference text left in English) and produces a literature summary. Wraps a Python pipeline (parse, rebuild, verify) as 16 DeepSeek Harness tools.

27 days agoTools & CapabilitiesMIT
J

dsh-code-review

jkin8010/dsh-code-review

Code review center for DSH, built on open-code-review: reviews current changes, commits, branch ranges, project architecture, code modules and business data flows, with live progress, a GitHub-style commit heatmap, fixed markers, automatic fix verification, light/dark themes and one-click fix sessions. Needs git; AI review also needs the open-code-review CLI 1.13 or later (npm i -g @alibaba-group/open-code-review), and the reviewed code goes to that CLI's configured LLM, or to the session model when the review is delegated to it. The engine is picked automatically — that CLI's model, then the session model, then offline structural analysis — so findings still come back with no API key; reopening a report after a fix session re-runs the review to verify the fixes.

28 days agoDev & Plugin ToolsApache-2.0
2

image-scout

2039108952x-lab/image-scout

Search Wikimedia Commons and Openverse for real photos, download them, and verify provenance, magic bytes and dimensions before they reach your agent.

215 days agoSkillsMIT
X

dsh-session-transfer

xiaolin233-ctrl/dsh-session-transfer

Adds a "Move to another workspace…" row to every conversation menu: copies the full event log into the target workspace under a new session id (header, title and model preset preserved, delivery markers retargeted), reads the copy back to verify it, attaches it, then archives the original unless you keep it.

217 days agoSessions & MessagesMIT