Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
1208 plugin trovati
dsh-llmwiki
chancelu/dsh-llmwiki
Wiki Markdown locale come memoria a lungo termine per DeepSeek Harness — portato da llmwiki
dsh-llm-codebuddy
shatyuka/dsh-llm-codebuddy
Plugin Tencent CodeBuddy per DeepSeek Harness (dsh)
pa-dsh
conradlu2740/pa-dsh
Gruppo di plugin ProactiveAgent × DeepSeek Harness: memoria proattiva + suggerimenti proattivi integrati in DSH (bundle aggregato, installazione con un clic tramite dsh plugin add)
dsh-feishu
itr-del/dsh-feishu
Bridge IM Feishu (Lark) per DeepSeek Harness tramite `dsh plugin add`; un utente DM per una sessione dsh persistente, con documentazione di debug completa
dsh-mcpguard
chenlaoshiyf/dsh-mcpguard
Analizza skill e configurazioni MCP alla ricerca di prompt injection, omoglifi, Unicode nascosto, comandi shell pericolosi e fughe di credenziali
noatmark-dsh-plugin
ylwl1997/noatmark-dsh-plugin
Igiene del testo come plugin dsh: sanifica testo non attendibile, analizza i caratteri invisibili, ripulisce la formattazione degli LLM ed esegue l'escape delle formule per prevenire l'iniezione CSV
dsh-pixel-report
qinghuidaqzp/dsh-pixel-report
Turns your agent's day or week into a shareable 1080x1632 retro pixel-art battle report card in a right-sidebar tab. Passively observes llm/stream, tools/result, session/event and workspace/changes to render real files and lines changed, commands run, sessions and turns, estimated DeepSeek cost and cache savings, a 24-hour (or 7-day) pixel bar chart, a pixel whale mascot, and a deterministic RPG rank title. Includes three color themes (DeepSea, GameBoy, Arcade), a privacy toggle to hide file and workspace names, PNG download and clipboard copy.
dsh-wechat-clawbot-access
linkadsl/dsh-wechat-clawbot-access
Pure-script WeChat ClawBot (iLink) bridge for DeepSeek Harness: configure SSH and port forwarding, then receive IPv6, SSH and token access info in WeChat and open the DSH Web UI on a phone. Includes QR login, owner approval and daily pushes, with no Agent or LLM tokens.
dsh-subagent-model-guard
a-molecule-of-atp/dsh-subagent-model-guard
Gates subagent delegation against DSH's official model allow-list, and can replace the delegation and model-discovery tools so a session snapshot cannot hide newly published models. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-skillmcp-gate
ciskonc/dsh-skillmcp-gate
Per-session and global exposure gate for skills and MCP tools — checkbox toggles in a sidebar panel and a settings page; denied items are removed from the model's tool/skill catalog on the next message, with batch apply, draft diff preview and per-session persistence. Needs DSH 0.2.0+.
dsh-chatgpt-to-memory
wojiao42/dsh-chatgpt-to-memory
Complete memory-import pipeline for DSH: runs the official ChatGPT export with automatic email-code re-authentication, transfers and verifies the download, deduplicates processed conversations, distills durable facts, interests and viewpoints through the host LLM service, and merges them through dsh-long-term-memory. Does not write memory files directly.
dsh-zh-yayan
arthurzhu1992/dsh-zh-yayan
Thought and word, both in Chinese. DSH opens in Chinese, all the way down — Chinese reasoning and thinking for the main agent, subagents, teams and background tasks. What it claims, you can verify.
dsh-atomcode
wellsoren/dsh-atomcode
Connects the models in the AtomGit AtomCode CodingPlan to DSH. Once installed, the model selector gains an AtomGit AtomCode provider and the chat window works as usual; a new AtomCode icon in the left rail shows login status, plan quota and 60-day usage. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-local-model-worker
cloudylapis/dsh-local-model-worker
Starts a local OpenAI-compatible model server only when the model is about to be used and unloads it after an idle period, with presets for LM Studio, Ollama and llama.cpp, custom start/stop commands for anything else, and a local_model tool for status, start and stop. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-cache-doctor
qinghuidaqzp/dsh-cache-doctor
Explains DeepSeek prompt cache misses in a right-sidebar tab. It observes system-prompt/assemble and llm/stream, compares each request with the previous one in the same session, and names the first part that changed: a system prompt section (shown before and after, with the changed characters marked), the tool list, rewritten history, an expired cache or compaction. Shows today's hit rate, money the cache saved, avoidable extra cost at DeepSeek's peak and off-peak list prices, the last requests and seven days of totals.
dsh-loan-cal
aaalittlecloud/dsh-loan-cal
Strict-convention loan math for DeepSeek Harness: real APR from installment fees, amortization schedules, bank-statement audits, prepayment break-even, offer comparison and LPR repricing. Zero dependencies.
dsh-andrej-karpathy
echo-ix/dsh-andrej-karpathy
Adds an on-demand coding-guidelines skill covering assumptions and tradeoffs, simplicity, surgical changes, and verifiable goals, adapted from Andrej Karpathy's notes on LLM coding pitfalls.
dsh-stocklab
zsimeon/dsh-stocklab
Stock analysis workspace for A-shares. Sidebar panel embeds the local stocklab web UI (quotes, LLM stock analysis, market review, hotspots) with a service status light and manual start button, plus a `stocklab` agent tool, FastAPI service supervision, and credential-safe API key injection via the DSH credential store.
dsh-geo-report-to-fix
liuhange789/dsh-geo-report-to-fix
GEO audit to fix pack: fetch one URL with the platform fetch (10s timeout, redirects, charset-aware decoding, 2MB cap) and score 11 weighted checks — title length, meta description, single H1 plus H2s, Organization and WebSite JSON-LD, `/llms.txt`, canonical, `<html lang>`, image alt coverage, page-level structured data, robots indexability — then write the two files the site is missing: `llms.txt` built from the page outline and `jsonld.html` with ready-to-paste Organization/WebSite JSON-LD, alongside an HTML audit report with the fix list ordered by weight. No browser, no third-party dependency.
dsh-mtrans
amahahanasaki/dsh-mtrans
Four DSH tools for translating MTool-format game scripts: mtrans_info analyses a ManualTransFile.json, mtrans_prepare splits its text keys into chunk files, mtrans_apply merges the translated chunks back, and mtrans_translate runs the whole file through a registered LLM provider (Japanese or English to Chinese).
dsh-server-memory (dsh-server-memory)
methpia/dsh-server-memory
Self-hosted project memory for DSH: a compact prompt index, search and save tools, and up to one consolidation per day written back to your own memoryd service, which runs on your laptop, a LAN box or a cloud server and never calls an LLM itself.
dsh-qwen-reasoning
jasocheung/dsh-qwen-reasoning
Auto-enhances manually-declared Qwen models with the full reasoning-effort levels (off/minimal/low/medium/high/xhigh/max) and defaults to max. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-enhance-prompt
tong174/dsh-enhance-prompt
One-click prompt enhancer: rewrite a rough composer draft into a clear, specific prompt without changing the ask, with one-click revert — reverse-engineered from WorkBuddy and benchmarked ahead of it.
dsh-prompt-smith
cyberpzy/dsh-prompt-smith
Adds a sparkle button to the DSH composer's tool row that rewrites the current draft into a structured prompt through one auxiliary call over the profile's own LLM route, writes the result back into the input (Ctrl+Z restores the original), fences the draft against prompt injection, and never touches the session log; a settings page selects provider, model and reasoning effort from the host's own model catalog with a test call that reports unsupported effort levels, edits the built-in system prompt (persisted through the host config editor), and tunes temperature, max tokens and max draft length. Zero dependencies, no build step.