DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
37 个项目，匹配「lan」
EricJiang0423
Local-first issue board for DeepSeek Harness: board data, model-facing tools, a fresh-agent planning loop, and a human approval queue for agent-proposed issues.
JuwanXu
DeepSeek Harness plugin for fail-closed network recovery, recommended answers, decision learning, and unattended continuation.
RayYeung1989
DeepSeek Harness (dsh) ↔ TencentDB Agent Memory (TAM) long-term memory bridge: L0 conversation capture + recall injection via TAM v3 data plane
TIREEDMAN
木兰辞 · MulanCi — 多 Agent 编排与逐 Agent 认证管理；DeepSeek Harness 第三方源码预览 / multi-agent orchestration source preview
alanzhao0128
Lightweight zero-dependency long-term memory for DeepSeek Harness: Markdown memory store, L0 catalog injection, 5 model-facing tools, background extraction. | dsh 轻量跨会话记忆插件
anonRTtty
DSH (DeepSeek Harness) mobile remote mode plugin - LAN discovery, QR pairing, Level-1 observer and Level-2 remote prompt from Android/iOS phones and any browser. Multi-platform, early development (Dev0.1).
ayanJava111
deepseek harness思考过程中文插件
luyu020816-droid
该仓库暂未提供项目说明。
yukitakasama
Single-session context anatomy for the DSH Web GUI: attribution, headroom planning, and a context x trajectory timeline — not another usage ledger.
ChenneyZhuang
Estimate-before-build skill: bounded task list, S/M/L/XL band estimates with uncertainty drivers named, scope-vs-budget options surfaced to the user, and estimates recorded for finish-line calibration.
Jaffe2718
System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.
harmless0819-dev
Turn-injection message channel between DSH agents on two machines: messages land in a log and are injected as context at the next agent step.
qingyou002
DSH plugin: hands a long session over to a fresh session in the same workspace on /handoff or at a token threshold, carrying the preset, model, permissions and plan mode across; the brief is written by the session's own model and the switch waits for a step boundary instead of interrupting running work.