DeepSeek Harness bundle for AI NetCafé's hosted tools. One install for the full catalogue, or pick one of four focused packs (tables, dev kit, doc flow, China facts) so you only pay the context cost of what you use.
メモリ・ナレッジ · Agent 連携 · 金融データ · サービス連携 · 生産性ツール
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mario03690/dsh-netcafe
Observational memory for DeepSeek Harness: background observers distill session work into observations and durable reflections, so long sessions survive compaction with their decisions intact.
メモリ・ナレッジ · 生産性ツール
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EPCN-fla/dsh-observational-memory
A typed, inference-capable ontology (TBox + ABox) plugin for DeepSeek Harness — durable domain knowledge the agent can define, assert against, and query under schema constraints.
メモリ・ナレッジ · Agent 連携
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tancheng33/dsh-ontology
OpenKapsel workspace bridge for the DeepSeek Harness: operate a remote OpenKapsel workspace (files, shell, context, memory, sharing, preview) through skill-driven tool calls using only its workspace URL and control token.
DeepSeek Harness plugin: give the agent a switchable, persistent persona (人设) with cross-session memory. Built-in personas an-ruotong / yan-guan / lao-jie plus user-defined personas; switch_persona / list_personas / persona_remember / persona_recall / persona_forget tools.
メモリ・ナレッジ · Agent 連携 · 生産性ツール
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:haimuhaimu/dsh-persona
pet 2.0 (beta) — a standalone Hermes-brained desktop pet for the DSH web GUI. A whale-girl sprite that talks to a local Hermes Agent (long-term memory + persona), independent of the original @linxin666/dsh-pet.
メモリ・ナレッジ · Agent 連携 · インターフェース
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Theathens/dsh-pet-hermes
Cross-disciplinary association popup for DeepSeek Harness: pick the disciplines you care about, then draw a card — the LLM offers one concrete structural link between another field and what you're currently working on. A tool for thought (a hook, never a finished analysis), surfaced faint and ignorable over an in-memory Connection RPC channel, never the session log.
Verification-gap probe for DeepSeek Harness: a backend plugin that watches each user turn, judges steer/ride/neutral with a cheap LLM, and accumulates how far the AI's autonomous progress has outrun what the user has actually verified — surfacing a faint, ignorable prompt (over an in-memory Connection RPC channel, never the session log) when they've drifted out of grasp.