@meilulin-1992/dsh-moa
Mixture of Agents for DeepSeek Harness: /moa marks a message, multiple reference models assist the main model's summary.
1140 results
Mixture of Agents for DeepSeek Harness: /moa marks a message, multiple reference models assist the main model's summary.
Session settings, MCP servers, and Skill management plugin for DeepSeek Harness (DSH) Web GUI.
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.5-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.
Ask any line of code its backstory: what it does, and why it's here — grounded in git history and the agent's own session log. Ships a DeepSeek Harness plugin and a standalone MCP server.
智谱 MCP 三件套 for DSH:联网搜索(search)、网页读取(reader)、开源仓库(zread)原生 provider 与工具,附设置页卡片。Zhipu MCP suite (web search / reader / zread) as native DSH providers and tools, with a settings card.
AI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint, with multi-provider support, model discovery, and agent tool registration. 与 @xiaoyuink/dsh-image-vision 同系列的图像插件。
Diagnose WSL/Windows proxy, Node 24 fetch, dsh web process env, proxy TCP listen, DeepSeek/npm/ModelScope reachability.
Skill studio for DeepSeek Harness: visualize all agent skills, view/edit their SKILL.md bodies, toggle model/user invocation, and mine session logs to extract reusable personal skills (auto-loadable by the agent) — from the web settings panel (Skill 工作台) and via skillmgr_* / skillmgr_extract_* tools
GLM 视觉模型插件:注册 glm-vision 供应商路由(glm-4.6v 系列,image+text 输入声明)并提供 glm_vision 工具,让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。
Sync cc-switch provider profiles (Claude Code / Codex relays) into DeepSeek Harness as llm-pi-ai routes, credentials stored via the DSH credential seam.
DeepSeek Harness 插件:数学建模竞赛自动化论文撰写系统 v3(中控台双重质疑 + 五阶段流水线:扫描验证/评审决策、P0-P3 评级与阶段级回滚、教训持久化、索引导航、兜底定稿 Final_Paper.md、断点续跑、进度面板)
AWS Kiro (CodeWhisperer) adapter for the DeepSeek Harness LLM seam: Claude and open-weight models through one signed-in Kiro account
DeepSeek Harness bundle for a Windows desktop UI context picker and MCP server for Codex, DeepSeek Harness, and AI agents
DeepSeek Harness plugin: tokensforce gateway integration — login onboarding, provider profiles, and the usage dashboard tab
Local-first task outcome ledger & acceptance plugin for DeepSeek Harness (DSH): evidence-backed verification of task completion, zero extra model cost, user-owned sidecar data. 任务结果账本与验收插件:机械证据验收、默认零额外 token、数据本地持有。
dsh LLM adapter plugin that bridges Devin Connect RPC into the dsh model provider system, with dynamic model catalog, settings panel integration, and Devin CLI credential auto-detection.
Genuine Liquid Glass theme for DSH Web UI: SVG feDisplacementMap edge refraction on input card, send button, bubbles, view tabs, queue dock and sidebar. Built-in animated demo wallpaper, customizable background blur & brightness, redesigned model selector popup, glass-styled buttons, and a unique water-drop settings icon.
Shows the selected model provider's account balance next to the composer model seat once a model and reasoning effort are selected.
Switch the current DSH session's model with a natural-language sentence, on web, TUI, or IM bridges (WeChat, Feishu, etc.).
Two-tier model router for DeepSeek Harness — automatic execution/judgment routing with LLM Judge, multi-model fallback chains, and exponential-backoff runtime failover. A DSH adaptation of pi-shift-router.
Model-facing Windows search tool backed by the Everything index (Everything64.dll FFI via koffi)
Model-authored context pruning for DeepSeek Harness through the official compaction API.
Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness