Layered memory plugin for DeepSeek Harness (dsh) — auto-distills conversations into L0–L3 memories (raw dialogue → atomic facts → scenes → persona) and injects relevant context before every model step. Pipeline ported from MemoryCore (TencentDB-Agent-Memory).
A DeepSeek Harness tool plugin that lets text-only agents "see" local images — auto-detects the real format and returns a detailed text description via any OpenAI-compatible vision model.
A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.
KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.
Give a DeepSeek Harness agent a voice it owns — offer_call rings the human (接听/拒接/稍后); local TTS via CrispASR + Qwen3-TTS CustomVoice, 9 speakers, 2 Chinese dialects. Local-first, offline-capable.
Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, budget caps with threshold alerts and over-limit policies, carbon footprint estimation, per-model latency benchmarks, a Settings budget tab, and the /budget command
Conversation history recall for DeepSeek Harness (DSH) — literal/fuzzy/semantic retrieval of every past conversation, fully local & offline. AI never forgets what you told it.
一个将Claudecode的dev-team插件兼容到dsh的套壳插件, token使用很快, 非使用dsh中重度开发的谨慎使用. A wrapper plugin that ports Claude Code's dev-team plugin to dsh. Heavy token usage — use with caution unless you're doing intensive dsh development.
VPS Hub for DeepSeek Harness: SSH ledger plugin — agents discover, test, execute on, and transfer files to your cloud servers. Keys stay local as path references.
