Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

513 plugins found

J

dsh-skill-pack

jeremy9682/dsh-skill-pack

11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) as an installable skill pack.

53 months agoSkillsMIT
Q

dsh-rugu (dsh)

qiuyedx/dsh-rugu

Persona memory for DeepSeek Harness: one memory shared by every entry point (DSH desktop, and QQ through the dsh-qq bridge) that records what the agent itself experienced. Raw messages are kept, five recall routes (vector, keyword, people and events, time, who is present) run before each reply, and a per-context check decides whether a remembered thing may be said. Adds memory_recall, memory_note, memory_fix and memory_look tools and a Settings page; embeddings are optional (local Ollama or an OpenAI-compatible endpoint).

47 days agoMemoryMIT
B

dsh-cloudflare-connector

beings-labs/dsh-cloudflare-connector

Shared Cloudflare access for agents and plugins through browser OAuth and the official MCP server, with upstream tools, automatic token refresh, and a typed plugin service.

47 days agoTools & CapabilitiesMIT
L

dsh-market-watching

leni-more/dsh-market-watching

A market card pinned to the DSH sidebar: live price and 24-hour change for crypto pairs, A-share / Hong Kong / US stocks and world indices, FX majors and London spot gold and silver. An optional long or short cost basis plus a position size turn the change column into a P&L percentage and a cash amount; symbols, order and refresh interval are chosen in DSH settings. No login and no API key. Quotes come from public endpoints of Gate.io, Eastmoney and Sina, and the symbols you choose are sent to them on every refresh.

411 days agoUI EnhancementsMIT
R

dsh-aside-note

rayle8/dsh-aside-note

AsideNote (旁边记) is a lightweight notes and todo list beside the conversation: a button at the top right of a session badges the open count and opens a resizable right-side panel. Notes default to one list shared across the workspace, with a switch back to the current session, and are stored in a DSH host file, so refreshing, restarting or switching browsers keeps them. Check items off, reopen completed ones, clear completed behind a confirm, copy, edit or delete, and forward a note to the open composer with a custom prefix (never auto-sent). Drafts are saved per workspace, and the panel follows the light/dark theme and all 8 DSH languages.

420 hours agoUI EnhancementsMIT
C

dsh-plugin-session-share

cjxiao0718/dsh-plugin-session-share

Export any DeepSeek Harness session as a single self-contained HTML page that opens offline, with per-message picking, collapsed tool calls and default redaction of local paths and credentials.

427 days agoSessions & MessagesMIT
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.

415 hours agoSessions & Messages
L

dsh-model-gateway

leafyezi233/dsh-model-gateway

Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates share one named group with ordered, balanced or random dispatch; upstream failures before any output switch to the next candidate transparently, and rate-limited requests are retried after the provider's backoff. Per-candidate call statistics (attempts, answers, failures, token/TTFT totals) appear as badges in the settings page, and daily aggregates persist to a local file with a 30-day heatmap and trend view. Until you create a key in the UI, the endpoint accepts calls from anyone who can reach it; keys (stored as SHA-256 hashes) then turn authentication on, and the endpoint stays locked even after the last key is revoked. Exposing the optional LAN listener without a key leaves the port open to the whole network. Runs on DSH 0.1.2-rc.1 through 0.1.7-alpha.1 and later.

418 days agoModels & Providers
P

dsh-plugin-kit

perrylink/dsh-plugin-kit

Shared toolkit for authoring DeepSeek Harness plugins, published as @perrylink/dsh-plugin-kit: a pluggable provider registry seam, fail-closed approval and session-event gates, shared sanitize/pricing/judge modules and a new-plugin skeleton.

420 days agoDev & Plugin ToolsApache-2.0Archived
S

dsh-suite

stardustlc666/dsh-suite

Plugin bundle (@stardustlc/dsh-suite) that composes shared Cordis and Minimal-PTC configuration patches across 18 pinned plugins, with 10 native workbenches, 5 switchable workbench themes, lifecycle cleanup and inline bundle update/rollback controls; components remain independently installable, while Review and Computer Use ship separately.

416 hours agoWorkflow & AutomationMIT
M

dsh-forge

maxmilian/dsh-forge

Read-only Gitea and Forgejo tools over the REST API both projects share: instance info, repository listing, issue and pull request search and read, PR diffs and changed files, and Actions runs, jobs and job logs. Tool metadata is available in English, Traditional Chinese, Simplified Chinese and Japanese.

42 months agoGit & Code ReviewMIT
0

dsh-crypto-portfolio

0xrabit/dsh-crypto-portfolio

Self-hosted crypto portfolio dashboard: BTC, EVM (73 chains via DeBank), Solana, Dogecoin, Cardano, Hyperliquid L1, five exchanges (Binance, Bybit, Backpack, OKX, Bitget) and tokenised equities in one view, with multi-provider failover, custom asset labels, a tunable asset-health report, a shareable PNG card, per-source connection tests, multi-profile configs, scheduled refresh and zero-dependency charts (Python stdlib + vanilla JS, no CDN).

49 days agoTools & CapabilitiesMIT
D

dshhub-market

dshhub-co/dshhub-market

Passcode marketplace inside DeepSeek Harness: enter a six-character code to unlock and install plugins shared by creators, plus themes, backup, updates and diagnostics.

42 months agoDev & Plugin ToolsMIT
L

dsh-plugin-heartbeat

littleblacktong/dsh-plugin-heartbeat

Autonomic heartbeat for each root agent: silent pulses diff the session's todos, Agent Team board and goal against what the last pulse saw, and speak only on a signal — L1 report, L2 ask (ask_user_question), L4 escalate — never starting work. Each message carries a why-now line, an optional one-line physiology signature (time since your last message and how many times it has reached out today) and a compact task snapshot (800-char cap); a dedupe window, quiet hours, a daily budget, refractory/restart cooldowns and persisted vitals keep it quiet, while busy-safe followup injection never stacks. It shares one advisory speech floor with dsh-plugin-memory (~/.dsh/proactive-cooldown.json, 180 s) so the two never talk over each other, stays silent while a child subagent or teammate is still working, and surfaces a "subagents working · N" pill in the conversation header (polling pauses while the tab is hidden). v0.8 adds a diagnostics panel that explains recent quiet pulses and names the current speech-floor holder, plus panel controls for the arbitration window, presence suppression and the physiology line; its settings section carries a stroked heart mark (16×16, stroke 1.3, same spec as dsh-plugin-memory). v0.8.1 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 0.8.1 or newer.

411 days agoWorkflow & AutomationMIT
T

dsh-astock-research

tiantianlaolao/dsh-astock-research

China A-share stock research: ticker search, announcements over any date range, financial report cards, valuation profiles and signal-factor explanations (~5,000 stocks since 2011, public read-only data service), plus a link-out tool to an external trading-sandbox product.

43 months agoTools & CapabilitiesMIT
K

dsh-trading-toolkit

kentleenot/dsh-trading-toolkit

A-share and US stock trading toolkit for DSH agents: realtime quotes, OHLCV klines, ADX three-state regime signals and simple backtest previews via EastMoney. Read-only, never places orders.

43 months agoTools & CapabilitiesMIT
A

dsh-visual-intelligence-engine

alccs/dsh-visual-intelligence-engine

Visual Interactive Engine — interactive graphics with native Harness prose; structured input, local repair and shared controls

316 days agoUI EnhancementsMIT
S

dsh-dungeon-master

superchipper/dsh-dungeon-master

QQ Bot channel and D&D 5e Dungeon Master plugin for DeepSeek Harness (fork of @tencent-connect/dsh-qqbot; do not enable alongside upstream): /dnd runs turn-based campaigns with 19 `dnd_*` tools for dice, checks, grid positioning, fog and battle maps, story chronicles, snapshot rollbacks and an optional dedicated combat subagent, plus /persona per-chat switching with handoffs, shared Markdown notes, sticker collection, read-only Bilibili tools and per-chat tool-access gating. Direct and group chats default to open in cordis.patch.yml while non-allowlisted QQ chats are blocked from shell and subagents; requires QQBOT_APPID/QQBOT_SECRET or in-app QR binding, with optional sharp for rendered maps and ffmpeg for audio/video. Shared notes are visible to every session, so private-chat content may be recalled in groups.

35 days agoIntegrations & RemoteMIT
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.

35 days agoModels & ProvidersMIT
C

dsh-remote-console

cccodder/dsh-remote-console

Right-sidebar SSH terminal for DSH where you and your agent share one PTY: 16 agent tools, configurable transfer limit, session-isolated audit trail, one-click in-place updates.

32 days agoIntegrations & RemoteMIT
C

dsh-lane-bridge (dsh-lane-bridge)

cnranger1124/dsh-lane-bridge

Multi-channel IM bridge for DeepSeek Harness: each QQ (SnowLuma / OneBot v11, official QQ Bot) or Discord group and private chat becomes its own agent session, bound to a role card whose domain carries knowledge bases with draft approval, shared memory, a read-only GitHub reader and group trigger rules; two built-in personas (customer support, group chat), unified push with broadcast, and human hand-off.

326 days agoIntegrations & Remote
I

dsh-mnemosyne

i11ustrious/dsh-mnemosyne

Layered long-term memory for DeepSeek Harness: each turn injects a persona frame plus a relevance-ranked memory index while full transcripts stay on disk and are expanded on demand, so the vault never floods the context window. Facts are slot-keyed, so a changed mind retires the old value instead of recalling two contradictory answers. The persona frame is derived from memory by the model itself, behind three anti-pollution gates (rejecting development chatter, blocking echoes of its own injection, and merging restatements by shared content words). Periodic consolidation merges near-duplicates, rolls long topics into digests, and archives low-value old entries by tagging only — raw text is never deleted. The append-only store is compacted in place (measured 4.7 MB to 355 KB). Zero third-party dependencies, no build step. Note: per-turn injection inevitably lowers prompt-cache hit rates, so this plugin is not recommended for work scenarios.

327 days agoMemoryMIT
Y

harnmem (dsh-harnmem)

ys118/harnmem

Cross-harness agent memory for DSH: one plain-file store shared by the DSH and pi adapters and the harnmem CLI, so a memory written in one harness is available in another; injected as a byte-stable hot index, with five harnmem_* tools, session-end extraction, and a read-only memory browser panel.

312 days agoMemoryMIT
C

dsh-codex-history

chameleonn4/dsh-codex-history

Install it by asking DSH in one sentence, then it reads your local Codex CLI/Desktop chat history from ~/.codex/sessions and makes it usable inside DeepSeek Harness: a panel under the composer lists sessions with keyword and date filters and one-click import, the codex_history tool lets an agent list, read, search and summarize past conversations, a session whose working directory matches is injected automatically when a new agent starts, new Codex messages arrive as incremental updates in the running conversation, and a shared folder can mirror both Codex and DSH sessions across machines. Read-only — nothing is written back to Codex.

326 days agoSessions & MessagesMIT