Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

26 plugins found

S

dsh-blender-plugin

sixtysevenlf/dsh-blender-plugin

Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.

2.2k6 days agoTools & CapabilitiesBSD-3-Clause
O

agent-crop

oriliz/agent-crop

Times AI coding sessions, nudges long-running turns, and keeps a local work ledger with a collector-health dashboard, so you can see where the time actually went. It also records retrospectives and routes each lesson back into agent instructions, skills, or tooling.

5618 hours agoMemoryMIT
L

dsh-plugin-memory

littleblacktong/dsh-plugin-memory

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory. v0.11 added a bilingual settings panel whose copy and sidebar label follow DSH language setting (中文「记忆」/ English "Memory"); v0.12 added the shared cross-plugin speech floor, a context-sensitive tone section and a weekly growth recap; v0.13 declares its DSH compatibility via engines.dsh (official 0.2.1-rc.5 series; older hosts are refused by the gate), adds a "Review now" button (POST /api/memory/control, action growth-now) that sends one growth recap immediately while still respecting the speech floor, panel accessibility (aria labels, status and alert roles, focus-visible rings), and the public PROACTIVE-PROTOCOL.md. v0.14 adds per-session memory: a composer chip with a dropdown (this session / workspace default), the /memory on|off|status command, and a settings-panel switch all flip the same gate — off means no boot injection, no digest/recall nudges and no last_access stamping for that session (nothing is deleted); disabledWorkspaces lets whole projects default to off, and session choices persist for 7 days. v0.15 adds a Basic soul (quick forging) card: my name / what I call you / baseline persona, saved into a managed block inside SOUL.md (the rest of the file is left untouched) and marks BOOTSTRAP complete; existing chat-forged souls are echoed from the SOUL text, and the boot block now asks the agent to remind the user to forge first when no soul exists yet. v0.16 turns the memory graph into an interactive 3D sphere (Canvas, zero dependency): drag to rotate, wheel to zoom, drag nodes to arrange them in 3D, double-click empty space to reset, auto-spin (reduced-motion aware); hover or click a node to instantly light up its neighbours (displacement+duration click threshold), and colours adapt to light/dark panel themes. v0.17 adds graph search (ranked matches, the camera flies to the hit and lights up its neighbours), Reveal in Finder / Copy path for any node (the host command is awaited, and the absolute path is copied automatically when reveal fails), Windows support (path-variable expansion, CRLF parsing with style-preserving writes, explorer /select, argv and exit-code handling, case-insensitive workspace matching), plus a much shorter README with real screenshots. v0.18 (issue #8) adds a boot snapshot mode: session freezes the boot block for the session so mid-session memory writes no longer invalidate the prompt-prefix cache (the volatile recent-log tail now rides in its own late context segment), with live kept as the default; double-clicking a memory node now opens the note in the DSH right sidebar (falling back to Finder/Explorer). v0.19 makes the plugin compatible with DSH 0.2.2-rc.2: the agent registry is read with agents.roots() when available and falls back to agents.list() on rc.2, and every agent/created listener is exception-guarded — on rc.2 an unguarded throw there rejects agent registration and no session can be created, so rc.2 users must upgrade to 0.19.2 or newer (0.19.5 is latest). Settings, dashboard and composer chip keep working on both the legacy and the rc.2 host APIs.

392 days agoMemoryMIT
B

my-dsh-plugins (dsh-my-observability)

baosfeng/my-dsh-plugins

Observability and git tooling: a persistent cross-session event audit log with a query API, a resource watchdog sidebar panel, structured Conventional Commits and pre-commit incremental diff review (npm: `dsh-my-observability`).

182 days agoDev & Plugin ToolsMIT
S

DSH-chat-keeper

sky-lll27/dsh-chat-keeper

Manage DSH conversations: one cross-workspace table with batch archiving, body search over message text, and recycle-bin deletion you can undo.

148 days agoSessions & MessagesMIT
W

dsh-plugin-toolkit

wjddidi-1/dsh-plugin-toolkit

Preflight for plugin authors: the checks the market runs — root export, dsh.client against exports\["./client"], whether npm pack ships the panel — on any folder or GitHub repo, from a panel or one command; plus release tooling and a Node testkit for client bundles.

514 hours agoDev & Plugin ToolsApache-2.0
X

apk-reverse-skill

xiaotianya14/apk-reverse-skill

Mobile-first Android APK reverse-engineering skill for DSH and DSH Go — decode with jadx/apktool, locate ad SDKs and entitlement logic, patch smali or values, repack/align/sign, then verify on a real device. Installs the apk-reverse skill; all tooling runs locally in proot Ubuntu on the phone or on PC Linux.

318 hours agoSkillsMIT
B

dsh-omv

bx33661/dsh-omv

Evidence-first vulnerability research workbench for DeepSeek Harness: native audit views, 29 OMV tools, Evidence.v1 findings, reproducible runs, Campaign workflows, and isolated PoC evidence.

323 days agoTools & 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
S

KISS_Law-DSH

shaky77/kiss_law-dsh

English edition of Weiwen's Law (KISS's Law): the first and only domain-agnostic white-box causal adjudication middleware for AI agents. Unlike domain-specific causal-inference tooling (statistics/economics/ML) or evidence-gated agent firewalls, it adjudicates *every* tool call along a deterministic structural causal chain (R->S->D->H->M) before execution - across any domain, with no training or per-domain tuning. It blocks destructive and credential-file operations, escalates repeated boundary violations, cuts faulting links until verified-fixed, and gives risk verdicts on un-auditable execution; runs fully local with zero API cost.

215 days agoSecurity & PermissionsAGPL-3.0
V

dsh-clearview

vinzelles/dsh-clearview

Adds a Reading tab to the DSH web client that shows process steps and live reasoning in source order, collapses successful turns to the final answer, and keeps the original tabs, composer, and tooling intact.

213 days agoUI Enhancements
D

dsh-moa-native

ddl095/dsh-moa-native

Native generation-time Mixture-of-Agents: every turn, reference models run the same session context in parallel as pre-run drafts and one aggregator executes with full tooling; config-as-model recipes, F mirror / R trimmed views, enforced subagent gating (dual-shape session indexing), derived per-recipe vision (vision refs relay image reads to text-only aggregators), tiered cadence with separate steering and patrol rosters plus frozen reuse between beats, degeneration guard dropping degenerate reference output, anonymized model face (failure notices carry no provider identity), and cache-friendly guidance placement (the rehearsal record is pinned where it was produced instead of appended to every request, so the cached prefix covers it and each step pays only for what was added since - on by default across every cadence). Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

117 hours agoMemoryMIT
C

stavros-dsh-redteamer

csi-entitymorton/stavros-dsh-redteamer

Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).

13 months agoSecurity & PermissionsMIT
O

dsh-drive-backup

ozanstn1-stack/dsh-drive-backup

Rclone backup tooling with four tools: target inventory, local/remote status, rclone check verification, and approved copy/sync transfers with dry-run previews and an audit line. Requires rclone installed and a remote configured with `rclone config`; the plugin never reads the rclone config or credentials.

018 days agoTools & CapabilitiesMIT
C

dsh-guard-degen

chunqing286/dsh-guard-degen

Detect and contain runaway symbol streams at the model boundary in DeepSeek Harness, with tooling to repair polluted artifacts and sessions.

019 days agoTools & CapabilitiesMIT
D

dsh-adaptive

dingchenhui0618-arch/dsh-adaptive

Version-adaptive tooling for DeepSeek Harness: it reads the running DSH version from the plugin manager, mirrors app-boot plugin-compatibility rules (engines.dsh first, then @deepseek-ai/dsh* peers, prerelease-inclusive comparison, exact-version exemptions) to score every installed plugin, and statically flags source still using APIs renamed or deprecated between v0.1.6 and v0.2.1. Ships a conversation-view panel, an agent tool and HTTP state/scan/report routes. Read-only, offline.

023 days agoTools & CapabilitiesMIT
7

MCModsDevBridge

7starsseeker/mcmodsdevbridge

Development tooling for Minecraft 26.3 mods: starts a real dedicated server and a real client from JSON instance registrations, drives both through an authenticated HTTP probe, and asserts on world, UI and log state across Fabric, Forge and NeoForge, writing per-run evidence and shipping no game or loader files. Requires JDK 25 and a Minecraft 26.3 instance.

028 days agoDev & Plugin ToolsApache-2.0
J

dsh-quick-screenshot

jackengineer/dsh-quick-screenshot

One-click screenshot button that floats over every DSH page, with a second one in the composer tool row: it captures the DeepSeek Harness window (or the whole desktop with a modifier) using the host capture tooling and puts the PNG where it is useful — straight into the composer draft as an attachment, or on the clipboard when no composer is mounted. Windows-verified, with macOS and Linux backends; no dependencies and no build step.

0last monthUI EnhancementsMIT
S

dsh-mcp-manager

shiliu153/dsh-mcp-manager

MCP server manager for DSH: nine mcp_manager_* tools, a CLI and a web panel that list, validate, probe, add, edit, enable/disable and remove servers in ~/.dsh/cordis.patch.yml, search and install servers from the official MCP Registry, and locate or rotate stored credentials.

017 days agoTools & CapabilitiesMIT
M

dsh-repo-map

mkaliezz/dsh-repo-map

DSH plugin: dsh-repo-map

03 months agoTools & CapabilitiesMIT
M

dsh-evidence-task-board

mkaliezz/dsh-evidence-task-board

DSH plugin: dsh-evidence-task-board (npm package: @mkaliezz/dsh-task-board)

03 months agoWorkflow & AutomationMIT
M

dsh-dev-server

mkaliezz/dsh-dev-server

DSH plugin: dsh-dev-server

03 months agoTools & CapabilitiesMIT
M

dsh-api-client

mkaliezz/dsh-api-client

DSH plugin: dsh-api-client

03 months agoTools & CapabilitiesMIT
M

dsh-error-explainer

mkaliezz/dsh-error-explainer

DSH plugin: dsh-error-explainer

03 months agoTools & CapabilitiesMIT