Plugins
Browse, filter, and install DeepSeek-Harness plugins.
245 plugins found
dsh-forge-studio (plugin-usage-billing)
0x7a7a6572/dsh-forge-studio
Usage and cost view for DeepSeek Harness: aggregates real token usage from existing session logs, locks each cost at the price of its event time, and shows month and today spend against a budget from a sidebar card or an input-bar pill.
dsh-budget
perrylink/dsh-budget
Per-plugin usage budgets and cost caps on the llm/stream waterfall: per-model usage accounting, session and monthly budgets with warn/block transitions, latency windows, and a carbon-footprint estimate.
dsh-video-vision
destinhue/dsh-video-vision
Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.
dsh-bill
jannchie/dsh-bill
Cost tracking priced from an online catalogue (models.dev + OpenRouter, 8000+ models, each call priced at its own instant): a per-turn cost line, a Cost tab attributing spend to tool output / model output / system prompt / commands, budget, monthly forecast, ~166 live-rate currencies, and a bill_stats agent tool.
dsh-longterm-memory
bufan528/dsh-longterm-memory
Local Markdown long-term memory for DSH: an Obsidian-compatible vault, a sidebar management page, four memory tools, and budgeted per-turn recall.
dsh-switchman
mrzturn/dsh-switchman
Sessions and messages (`session`): the plugin operates on the live conversation — injects a dispatch protocol into the session prompt (delegation by default across six model pools with optional intent routing, optional Agent Teams collaboration, and tiered verification with independent review for larger changes), manages the context watermark (automatic folding, protected recent messages, persisted fold state, and watermark-triggered handoff) so long sessions stay within the context budget and token spend tracks the work instead of the length of the chat, and renders a session header badge with a Host/Client settings page; token tracking (`usage`, no bill calculation), read-only MySQL/Redis checks and doc skills (`skill`), and tool-call safeguards (`dev`) round it out. Every capability serves the session and its messages. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-cookie-meter
ridistant8-art/dsh-cookie-meter
Windows-only floating percentage meter for the DSH desktop (0.2.x) cookie jar: it estimates how much of the request-header budget the dsh-auth cookies occupy, turns red past half, and clears the jar on the next launch with one click, avoiding the lockout that hits after roughly 72 launches.
capital-generation (dsh-plugin)
v587d/capital-generation
China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.
dsh-plugins (research-mode)
creait-nl/dsh-plugins
Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.
dsh-companion
beijingwahw/dsh-companion
Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).
dsh-subagent-control (human-wait)
spacerelay/dsh-subagent-control
Keeps the PTC run_code deadline from firing while DSH waits for your answer, plan review or approval, so a question can stay open longer than the shipped 120 s budget.
dsh-bot
han102300/dsh-bot
Always-on AI teammate: hand it a recurring task in one sentence; dry-run rehearsal by default, snapshot before every real run, one-click rollback, CNY budget circuit-breaker, per-run cost transparency.
dsh-context-imports
ciskonc/dsh-context-imports
Reads the files that AGENTS.md references with @path imports and injects their content into model context, with byte budgets, compaction re-seeding and a six-language settings card. v0.5.x expands the imports of every instruction file the harness loaded (including a project AGENTS.md picked up mid-session, needs DSH 0.2.0+) and offers an opt-in live mode (off by default) that watches injected files and re-injects them on change, with settings-page controls; use 0.2.x on DSH 0.1.7.
dsh-context-lens
goodandready/dsh-context-lens
AST-based context compression, test log filtering, and token budget guard for DeepSeek Harness: strips redundant syntax, prunes noisy log lines, and enforces a token ceiling so the context window never overflows.
dsh-plugin-usage-meter
fancr-code/dsh-plugin-usage-meter
Local-first usage and cost meter for the DSH web UI: composer button with live session cost and balance; panel with a stacked per-model daily/7-day chart priced per effective list-price interval (official pricing page synced daily), monthly usage tiers with a canvas share card, 30/50/85% context-pressure warnings with one-click /compact, budget alerts, and an in-panel npm update check with one-click update.
dsh-ide-workbench (codeintel)
liangshoux/dsh-ide-workbench
Code intelligence for the DeepSeek Harness IDE workbench: local and semantic completion, go to definition, find usages, hover and signature help, plus the TypeScript, Python, Java/JDTLS and YAML language servers with their memory budget. Requires the dsh-ide-workbench plugin.
dsh-qwen38-compaction-fix
zhubaohi/dsh-qwen38-compaction-fix
Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.
TravelPlanner
ausertdream/travelplanner
Trip-planning agent preset for mainland China that answers in Chinese: queries 12306 train availability, Fliggy and Tuniu flight and hotel prices, and real Amap transit routes, checks closures and weather, and delivers a single offline HTML roadbook with draggable maps, three hotel price tiers and an itemized budget. Ships 9 skills, an environment doctor that walks users through missing API keys, and a patch for the 12306 MCP server; it plans and queries but never books or pays.
dsh-plugin-mcp
menotbobbybrown/dsh-plugin-mcp
Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.
dsh-model-router
neptune810/dsh-model-router
Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.
dsh-adaptive-context
icstick/dsh-adaptive-context
Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.
mosaic-memory-compress
turingcorp-net/mosaic-memory-compress
Forgetting-curve in-place dialogue compression for DeepSeek Harness: recent turns stay verbatim, middle turns are structurally dehydrated (zero-LLM), ancient turns fold into a bounded summary pair — unbounded conversations on a bounded memory budget.
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.
dsh-skillopt
wode25500/dsh-skillopt
Nightly self-improvement for your DeepSeek Harness agent: harvest past sessions offline, replay recurring tasks on your own API budget, and consolidate validated skills behind a held-out gate. Brings microsoft/SkillOpt's SkillOpt-Sleep engine to dsh as native tools plus a bundled skill - no weight training. Requires Python 3.10+ and the SkillOpt-Sleep engine (pip install skillopt).