实时扫描最新社区关于 DeepSeek Harness 发布的插件

DeepSeek Harness bundle that mounts gemini-web-mcp as mcp__gemini-web__* tools

Conversation↔worktree binding for DeepSeek Harness: one-click isolated worktree + branch per conversation, with a binding manager panel

Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents — V0 bootstrap foundation (installable/loadable plugin-bundle skeleton)

DSH hot-plug execution engine: a reliable install/enable/disable/rollback/audit service for plugin marketplaces, agents, and host plugins (execution layer, not a marketplace).

DSH 微信桥插件：turn/approval 推送到微信，微信远程监控/批准/驱动 agent（iLink 通道，持久去重/分段/合并/白名单）

A multi-platform IM gateway for DeepSeek Harness (dsh) — Feishu (Lark), WeCom (WeChat Work), and Telegram. Turn your dsh agent into a chat assistant reachable from the messaging apps you already use.

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets

kimi-tide（月汐）— Kimi Code subscription as a native DeepSeek Harness LLM provider, with built-in OAuth token management.

Bidirectional Lark/Feishu control bridge for DeepSeek Harness

Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards

Matter-aware legal workspace dashboard and document agent tools for DeepSeek Harness

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)

Local Markdown wiki as long-term memory for DeepSeek Harness — ported from llmwiki

MCP Center: a settings-driven MCP server manager for the DeepSeek Harness. Register Streamable HTTP (no-auth / Bearer token / custom headers) or local stdio MCP servers from a dedicated Settings page; their tools publish as mcp__<name>__<tool> to the model. Self-contained MCP client, no external MCP SDK dependency.

Progressive-disclosure MCP gateway for DeepSeek Harness: two fixed tools, precise schema search, lazy connections, and failure isolation

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse

Memory retrieval plugin for DeepSeek Harness (dsh): wiki double-link memory graph with 9 tools — search (hybrid vector + fulltext), read, list, link-scan, remember, forget, compile, health-check, and a resident retriever subagent

Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call

Control Xiaomi/Mijia smart-home devices from DeepSeek Harness, bridged through Home Assistant

DSH plugin: prompt the agent to dispatch image recognition to an opencode-go mimo-v2.5 subagent

Multi-tenant SaaS extension for DeepSeek Harness (DSH): tenant identity, session ownership, authorization boundaries, tenant-aware MCP, and audit.