Plugins
Browse, filter, and install DeepSeek-Harness plugins.
6 plugins found
dsh-nexttavern
a86582751/dsh-nexttavern
NextTavern is a long-form roleplay plugin for DeepSeek Harness 0.1.7-rc.2 Web, with character-card import and creation, worldlines, worldbooks, layered long-term memory, keyword/semantic/hybrid retrieval, character agents, and card or novel export. SillyTavern character-card import is supported; v0.2.9 fixes distribution and installation.
dsh-plastic-memory
kkl08/dsh-plastic-memory
Long-term memory for dsh that goes beyond the usual saving and recall with a built-in system for governing and maintaining memories. Checkups find redundant, conflicting or outdated memories and suggest how to handle them, and key changes only happen once you approve them. Saving, recall and checkups run in the background without interrupting the chat, and anything that needs you is sorted by priority. Scenes and memory types can be freely combined, and per-type injection, retrieval and source lookup, health reminder sensitivity, the injection budget and more are all quick to adjust from the GUI settings page, so what gets remembered and how is yours to decide and shape.
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.
deepseek-plastic-memory
yixianqzm/deepseek-plastic-memory
Partitioned long-term memory for agents, with folders as memory zones, a one-line index first, and a forgetting curve.
dsh-TradingAgents (npm)
vicfei/dsh-tradingagents
Multi-agent investment committee for DSH - analyst, bull, bear, risk and PM debate where every claim carries an evidence tag, abstention (PASS) is a first-class verdict, Buffett/Munger/Lynch/Wood guest seats critique the debate itself, and zero-key market data (CBOE quote/K-line/options-IV + SEC 10-K + nasdaq news, Yahoo-free) feeds an auditable IC-MEMO - 6 to 10 model calls per session.
DSH-DREAM
baiqieji-lulu/dsh-dream
A durable RAG-enhanced long-term memory layer for LLM agents, featuring holographic memory, state-slot conflict detection, and timeline retrieval. Requires Python 3.10+ and this repository's Python dependencies: create a venv and run pip install -e ".\[dev]" in the checkout before enabling the plugin (the bundled installer is a PowerShell script, i.e. Windows).