Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

2504 plugins found

S

dsh-custom-model

sayzwx/dsh-custom-model

Custom-model console for the Models page: manage hand-declared llm-pi-ai providers in one list, fetch the model list an endpoint serves, and fill each model context window, max output and the reasoning levels the endpoint accepts straight into the configuration. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

3yesterdayModels & ProvidersMIT
0

dsh-ima

0131kikimy/dsh-ima

Connect Tencent ima knowledge bases to the agent through 16 ima_* tools that list knowledge bases and documents, search, read document text, write notes and upload files, configured from a sidebar panel.

316 days agoTools & CapabilitiesMIT
G

spine-plugin (dsh)

ghabix/spine-plugin

Subtask-tree context manager for DeepSeek Harness (@spinejit/dsh-spinejit): adds spine_open, spine_close, spine_next and spine_spawn tools so the agent works on a persistent SpineTree, replaces closed subtasks with their submitted memories while keeping active work and earlier prefix tokens intact, and renders the live tree in the Web/Desktop input dock and dsh-tui status rows.

33 days agoSessions & MessagesApache-2.0
W

dsh-session-matrix

wanqiu12345/dsh-session-matrix

Run up to four native sessions side by side, trace how subagents connect, and hand work over before context compaction.

33 days agoSessions & MessagesMIT
Y

fishpet-release (fishpet)

ygc06/fishpet-release

DSH companion plugin with emotion state, persistent companionship context, and an opt-in single-screenshot screen tool.

35 days agoJust for Fun
A

dsh-codex-mode

airainal/dsh-codex-mode

Adds a Codex-style step driver to DSH sessions with progress text before tool calls, turn continuation while todos remain, and a remembered permission-menu switch.

34 days agoWorkflow & AutomationMIT
C

dsh-recollection

cqxsg/dsh-recollection

Lets DeepSeek Harness agents autonomously search and revisit original history from the current session that has been removed from the model's context by compaction. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

32 days agoMemoryApache-2.0
J

dsh-token-steward

jiamingshi-jsphys/dsh-token-steward

Runs an OpenAI-compatible gateway on your own machine. Several upstreams sit behind one base URL, and each request picks a model from capability tags, context window and current availability. A 429, a 5xx or a context overflow moves the request along the fallback chain inside the same call. Token usage and cost are recorded per route in a local ledger, and vendors, keys and prices are edited on a settings page.

37 days agoModels & ProvidersMIT
J

dsh-remedy (plugin)

jjjjjjjjnnjnn/dsh-remedy

A patch set for DeepSeek Harness that repairs fused tool-call argument text at the llm/stream seam and re-throws whatever it cannot prove: a call is dispatched only when every fragment parses to a plain object, the first call keeps its id and synthesized ones are marked, and a stream that cannot be split keeps its original error instead of a success. It also listens on agent/request-error to name the deterministic refusals it will not retry, answers per failure class which patch covers it and whether that patch is switched on in the profile you point it at, and reads multi-frame zstd session logs offline to count every turn ending and every error code. Everything it claims is registered with the seam it touches and the limits it does not cross; the resolver never invents a value and never downgrades a configured setting.

3yesterdayDev & Plugin ToolsMIT
L

dsh-agent-team-auto-orchestrator

loyalchiiina/dsh-agent-team-auto-orchestrator

Host-side orchestrator for DSH agent teams. Every turn it injects an 11-section orchestration methodology into the system prompt and backs it with a counting tool-layer gate, so parallel dispatch, task-board tracking, cross-session handoff, employee-pool reuse and preset routing become the default in any preset and any session instead of something you have to ask for. The gate counts real dispatches (subagent / subagent_fork / spawn_teammate) rather than words: a todo listing N unmarked items only needs the base threshold, items explicitly marked as parallel must be launched in one batch up to a configurable cap, and a genuine single-step task is exempt by writing one marker. Read-only tools (read, glob, grep, context-management tools) are never gated. Team members are woken up and reused before new ones are hired, and subagents are reserved for work that must run under a specific preset. Local-only settings (preset routes, domain keywords, profile name, active tier) live in <DSH_HOME>/team-orchestrator.local.json and never ship inside the package. Status is exposed on a loopback-only HTTP route. Zero telemetry, no hosted service, no account. Adapts DSH kernel 0.2.2-rc.1.

36 days agoWorkflow & AutomationMIT
D

dsh-plugin-context-mode

domush/dsh-plugin-context-mode

Native DSH support for context-mode (mksglu/context-mode), intercepting large tool outputs with SQLite FTS5 indexing, BM25+RRF search, and session continuity. On by default: tool outputs over 4 KB are replaced with a short preview while the full text is indexed into ~/.context-mode/context.db, and a section is added to the system prompt. Its ctx_execute and ctx_batch tools run shell, Node, Python, PowerShell or cmd commands with DSH's own permissions and environment (not sandboxed), and ctx_index reads any local file path or fetches any http(s) URL it is given.

310 days agoMemoryMIT
P

dsh-locator

perrylink/dsh-locator

Whole-disk file-name search for DSH with a self-built cross-platform index, agent tools and a Web panel; no Everything required. It indexes your home directory by default; the first content search also builds a local full-text index (SQLite in the platform cache directory) of text and source files there (by extension, up to 1 MB each, 200,000 files) and of your recent DSH session messages; locator_export writes a SQLite copy of the index to any absolute path it is given, replacing an existing file when overwrite is true. The engine is a prebuilt Go binary shipped for six platforms (source in engine/), and the plugin makes no network requests.

3yesterdayTools & CapabilitiesApache-2.0
F

dsh-onmyoji-guide

free-swallow1/dsh-onmyoji-guide

Onmyoji game helper with five tools: shikigami and soul lookup, skill text, crit and panel math, NetEase Dashen guide search, and intro card paths.

320 days agoJust for Fun
A

agent-web-sandbox

ashenseeker/agent-web-sandbox

Sanitizes fetched pages before the model reads them: strips hidden text, offsite images and inline data, wraps the rest in canary-tagged untrusted delimiters, and flags prompt injection.

318 days agoSecurity & PermissionsMIT
J

session-stickies-manage-your-attention

juliiiiiiiu/session-stickies-manage-your-attention

Session-specific sticky cards with optional, explicitly authorized agent follow-ups. Targets the DSH desktop/web profile (protocol 0.2.2-rc.1); installed from GitHub.

3yesterdaySessions & MessagesMIT
M

dsh-session-handoff

mountbatten718/dsh-session-handoff

Session handoff: `/handoff` summarizes recent turns with an LLM, opens a new session in the same workspace with the summary as its first message, and can trigger automatically when the context window or session size grows. Supports DSH `0.1.0-rc.5`–`rc.8`, `0.1.1-rc.2`, `0.2.0-rc.2` and `0.2.1-rc.2`.

3last monthSessions & MessagesMIT
S

dsh-caveman

stevenwang15/dsh-caveman

Apache-2.0 port of the caveman skill family (JuliusBrussee/caveman) into DeepSeek Harness as 14 native skills — three terseness levels (caveman, ultracave, megacave) plus commit, review, help, stats, an in-session compress whose gate rejects a dropped code block, heading, URL, negation or env var, or a result that did not shrink, and six workflow-discipline skills; commands, paths and error text stay verbatim.

3yesterdaySkillsApache-2.0
Q

dsh-squeeze

q8atnight/dsh-squeeze

Adds a squeeze tool: the agent hands a long web page, a batch of pages, a text file or a text PDF (via pdftotext) plus one question to a helper model and gets back only the answer, so the material never enters the chat. A settings page picks up to three helper models from the DSH model list, each with a nickname, a fixed thinking level and a "when to use" note, with optional fallback and size limits taken from each model's context window.

316 days agoTools & CapabilitiesMIT
T

dsh-tiaforge

tia-forge/dsh-tiaforge

Bundles five TIA Portal skills (Siemens PLC docs lookup, ladder-logic generation, SimaticML-to-PNG rendering, scan-cycle simulation with PASS/FAIL scenarios, and a TiaLink gateway skill for driving a real TIA Portal project) and wires five MCP endpoints. Requires TiaLink (paid; Windows + TIA Portal V19/V20 + Openness) for real-project work, API keys for the four cloud services (100 free calls each, then paid; rendering is billed per call even on failure), Node 22+, and network access; program snippets are uploaded to tia.hubwiz.com.

35 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.

36 days agoModels & ProvidersMIT
R

dsh-agent-enhancer

rebornace/dsh-agent-enhancer

Agent enhancements for DeepSeek Harness Desktop: prompt history, one-click optimize with undo, next-prompt prediction, conversation and tracked-file restore, model bill, context details with compact, Auto routing, and per-provider DeepSeek balance.

3yesterdayUI EnhancementsMIT
W

agent-web-sandbox

wld12314/agent-web-sandbox

Sanitizes fetched pages before the model reads them: strips hidden text, offsite images and inline data, wraps the rest in canary-tagged untrusted delimiters, and flags prompt injection.

318 days agoSecurity & PermissionsMIT
S

dsh-gpt-image-playground

southcul/dsh-gpt-image-playground

Image generation and editing for GPT Image, Gemini (Nano Banana) and Grok, with official, OpenAI-compatible, api.toolify-ai.com and custom HTTP providers. Text-to-image, reference-image editing, canvas annotation, mask editing and Agent multi-turn chat, with images and history kept on your machine. The workbench UI is the MIT-licensed GPT Image Playground v0.9.0 build by CookSleep, bundled unchanged; that upstream is a standalone web app, not a DSH plugin.

37 days agoVision, Voice & MultimodalMIT
C

dsh-autocad-bridge (bundle-autocad-ui)

cmm00100/dsh-autocad-bridge

Drives the installed AutoCAD over COM and exposes it to the agent as 18 mcp__autocad__ tools: connect and status, cancel the current command, list registered ProgIDs, list or create documents, save, create and list layers, draw lines, circles, rectangles, polylines, arcs and text, list entities, zoom to extents, and pass any native command through. A sidebar panel owns the Python bridge process — start, stop, restart, dependency bootstrap, live logs and crash recovery — and resolves every path at runtime, so the same bundle serves both the web app and the desktop app. Windows only, Python 3.10-3.12, AutoCAD 2022-2024 documented (2024 is the default; other versions require setting CAD_PROG_ID to the matching ProgID).

313 days agoTools & CapabilitiesMIT