Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
2479 plugins encontrados
dsh-claim-gate
xizhilang2012/dsh-claim-gate
A self-justification gate for outbound claims: a claim needs a checkable source (an http(s) URL plus a quote of at least 8 characters), every number in the text must appear in a quote, and a quote whose vocabulary overlap with the post is under 10% counts as an invalid citation; absolute wording is rejected when the only evidence is second-hand. All verdicts come from deterministic rules — no model call, no network. The guard subcommand refuses to run the publish command when the gate fails (fail-closed), explains what is wrong and how to fix it, and requires an --ack note on the second attempt stating what changed; after three attempts it stops and hands back to a human. Ships check / explain / fix / guard, with 30 tests.
dsh-dev-toolbox
qingzhou-joshua/dsh-dev-toolbox
Sidebar developer toolbox with 65 pure browser-side tools in 13 groups — JSON, code formatting, URL, encoding, hashing, encryption, text, and number/date utilities — with zero network requests. Registers as a tab in dsh-better-sidebar, which must be installed for the panel to appear.
dsh-agent-desktop
mjnn/dsh-agent-desktop
Wraps the separately installed agent-desktop CLI (`npm i -g agent-desktop`) as nine DSH tools (ad_status, ad_list_windows, ad_snapshot, ad_find, ad_click, ad_type, ad_press, ad_launch, ad_close_app) so an agent can list windows, read an accessibility tree, click a snapshot ref, type text, send keys, launch an app and close it gracefully. The plugin adds no automation logic of its own: it validates arguments, calls the CLI and returns the parsed JSON envelope, and asks the caller to take a fresh snapshot instead of retrying a stale ref, so a click never lands on a shifted target.
dsh-arxiv-inspiration
lxion0553/dsh-arxiv-inspiration
arXiv paper survey assistant with a settings-page UI, a local knowledge base, a feedback loop, keyword search plus optional local-embedding semantic search, and per-paper deep-read notes. Requires a configured DSH LLM provider; semantic search and full-text deep read need an optional Python environment (pymupdf + fastembed), otherwise they fall back to keyword search or are skipped.
javmem-dsh-plugin
xuxiaoxiang0721-tech/javmem-dsh-plugin
Per-Bot memory for Tobs Bots (requires DeepSeek Harness with @botharness/core; it ships off with no Bots listed, and after you list a Bot and set mode to on it works with no other service): a read-only local full-text index of that Bot's own past conversations (Chinese words found inside sentences), memory imported from other AI tools, a status tool, optional auto recall before a step in which a Human speaks, and a service for other plugins. Richer backends can be chosen at install, with a quote first and a daily token cap: a public fact store (memv2-lite), the official Graphiti graph, or both, fed from the Bot's own conversations.
dsh-obsidian-quote (harness-plugin)
kleinklein0824/dsh-obsidian-quote
Adds a knowledge-base sidebar backed by the separately installed local Obsidian Quote service: select registered vaults or folders, retrieve read-only note excerpts and cited context, extract rules, generate project convention briefs, and view shared citation statistics.
dsh-session-find
quecai-niu/dsh-session-find
Literal full-text search across every DSH session log (Chinese sentences work, where the built-in FTS5 tokenizer fails), as a right-sidebar panel that scrolls to the matching line, plus a session_find model tool.
dsh-session-search
louisding9527/dsh-session-search
Agent-facing keyword search over local DSH session logs: session_search returns matching sessions with timestamps and excerpts, session_read dumps one conversation, and both skip injected context such as memory snapshots; no index is built.
dsh-strata
light-cheng/dsh-strata
Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.
dsh-scalpel
elegant01/dsh-scalpel
Compare two or three answers in one session and drop chosen turns from every later model request.
dsh-markdown-copy
drinkerqvb/dsh-markdown-copy
Copies a text selection anywhere in the DSH conversation as Markdown source on Ctrl+C, restoring headings, lists, GFM tables, fenced code blocks and TeX math.
dsh-prompt-optimizer
devzer0o0/dsh-prompt-optimizer
Rewrites the message you type into the DSH composer into a precise prompt before the model ever sees it, with one cheap side call on the session's own route. The rewritten text is what gets logged and sent, so the transcript always shows exactly what the model received; hover the whale to compare before and after. Slash commands, very short or very long messages and image-only messages are left alone, and any failure sends your text untouched. The composer whale is the switch: dark silhouette when off, gold when on.
dsh-stateful-responses
zhexuany/dsh-stateful-responses
Makes DSH's OpenAI Responses calls stateful: after the upstream confirms it stored a response, each turn sends only the newly added input items plus previous_response_id, and a stateless upstream is detected on the first response so every later request falls back to the full history.
dsh-model-pool
pure-cow-horse/dsh-model-pool
Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.
dsh-tlpro-models
dungcsnd1133/dsh-tlpro-models
Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.
dsh-draft-studio
wufeng0105/dsh-draft-studio
You type half a thought — "make me a scraper for Douban" — and the AI has to guess the rest. Click one button beside the input box and that line becomes a full instruction it can actually follow: what to build, what to output, what the limits are, how you'll know it's done. It never picks for you: where you haven't decided something (which library, which format), it lists the options instead of choosing one. The result is still a draft — never sent, and one click or Ctrl+Z puts your original back. Four presets (general / code / writing / translation), each one editable text you can rewrite to taste, and you choose which buttons appear. Optional: read the last few turns of the conversation so "that thing I mentioned" resolves correctly; use the current session's model or pin a specific one. Pure JS, no build, no bundled dependencies.
dsh-memory-router
dcd887/dsh-memory-router
Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.
dsh-offwork
snowbeatrain/dsh-offwork
A DeepSeek Harness page companion with animated characters, a clock-out countdown, estimated earnings, hydration reminders, quiet time and salary masking, with separate cards opened from the context menu.
dsh-sticky-notes-wall
skyline66/dsh-sticky-notes-wall
Sticky-note wall in the sidebar with pasted images and text, due reminders, done state, shortcuts, a pin-on-top floating window, appearance skins, and a native always-on-top Windows desktop window.
dsh-session-console
onlyinliu/dsh-session-console
Session Console: a sidebar dashboard over every conversation that shows run state, token spend, cache hit rate, context pressure and a heat score, resolves a plain-language sentence such as "how is the example project going" to the matching session, and dispatches that sentence as a queued task into it. Ships five agent tools (overview, find, tail, dispatch, cancel) over the same data.
box-select-copy
mi-chuan/box-select-copy
Alt+drag a rectangular box over the DSH conversation to copy the text inside it.
dsh-prompt-suggestions
heeweelee/dsh-prompt-suggestions
Composer suggestions for the DSH chat input: Up / Down step back and forth through every prompt sent in the current session — read from the session event log, so a message accepted from a prediction or sent by queueing counts too — Ctrl+Up opens a searchable history picker, and grey ghost text predicts the next message, accepted with the Right arrow. Every key only edits the draft; nothing is ever sent automatically.
dsh-sticky-wall
hahajing233-source/dsh-sticky-wall
Sticky notes on a wall, with five paper stocks, five inks, seven typefaces, four text sizes and your choice of pin, tape or clip.
dsh-tab-complete
furinalif/dsh-tab-complete
Predicts the next user message as composer ghost text using the configured DSH model; Tab fills the draft without sending, with time-aware context and cached suggestions.