@winterchenhuan/dsh-shadow-mind
Parallel cognitive runtime for DeepSeek Harness: heartbeat-scheduled shadow agents that review, fact-check, and work alongside the main agent
99 results
Parallel cognitive runtime for DeepSeek Harness: heartbeat-scheduled shadow agents that review, fact-check, and work alongside the main agent
Local tool-call failsafe and DWGR-8 personal governance proxy gate for DSH: blocks high-risk shell patterns, credential leaks, and enforces declarative param-level boundaries with hash-linked JSONL audit logs and optional Gateway.
动态滚动窗口子代理任务池:一次调用跑完整批独立任务,内部滚动补位,后台运行不阻塞主对话
Plugin Cordis para o DeepSeek Harness v0.1: interceta a camada HTTP (auth barrier sobre o fallback da Web UI) e orquestra subprocessos de longa duracao com ciclo de vida reversivel.
并行功能开发:文件所有权、接口契约、避免冲突、集成策略(垂直切片 vs 水平分层)。受 wshobson/agents(38k★ MIT)启发。
并行 agent 开发环境:Codex/ClaudeCode/OpenCode/Pi 并排跑,各在独立 git worktree——一个 prompt 扇出 5 个 agent 比较合并胜者;移动伴侣监控、终端分屏、Design Mode(点击 UI 元素送 HTML/CSS/截图进 prompt)、GitHub/Linear 原生、SSH worktree、AI diff 标注。受 stablyai/orca(49k★ MIT)启发。
Docker MCP Gateway 管理面板:经 SSH 在远端服务器执行 docker mcp 命令,管理 Docker MCP(列出/部署/移除 profile 中的 MCP、搜索/拉取 Docker MCP Catalog)。免构建(纯 ESM:Host 端 Node 原生 import + spawn python paramiko,Client 端零依赖纯 DOM)。
巴拉圭国家
Cross-provider second-opinion advisor for dsh. v2 (simple-extensible-configurable-stable): DEFAULT ROUTE = official DeepSeek (deepseek-official/deepseek-v4-flash); model param optional everywhere; one-page visual settings panel; honest audit trail. Scout mode = official + live web_search. OpenAI-compatible endpoint + consult tool + DSH_MODEL rerouting.
A crystal-structure visualization window for DeepSeek Harness (DSH): a 3D structure + Q-peak viewer and parameter panel, opened as a dsh-better-sidebar tab.
Side-chat (旁会话) plugin for DeepSeek Harness: launch a fresh, continuable parallel session from the conversation header while the main session keeps running. · DSH 旁会话插件:主会话进行中也能一键新开一个独立会话并行提问。
DeepSeek Harness (DSH) plugin: ✨ optimize the composer draft with the current model. Installable bundle (dsh.bundle + dsh.client); Settings tab controls on/off, generation params, and an editable system prompt with reset-to-default.
Multi-source web search tool for DeepSeek Harness — queries DeepSeek / DuckDuckGo / Exa / Google / Bing in parallel, merges results, fetches page content.
Pacote de idioma Português (Brasil) para a GUI Web do DeepSeek Harness
Local-first Skill load evidence, learning cards, and iteration preparation for DeepSeek Harness
An API testing sidebar panel (Getman) for dsh-better-sidebar: method/URL, params, headers, raw body, response viewer, shared history — with a host-side proxy that bypasses CORS.
Editable local and desktop dictation for DeepSeek Harness
并行多角色代码评审小队:/review 一条命令派出安全/正确性/测试/风格四名只读评审员子代理(每人可单独指定模型与思考强度),汇总为按严重度分组的结构化报告。Parallel multi-role code review squad: /review dispatches security/correctness/tests/style reviewer subagents (each on its own model) and aggregates one severity-grouped report.
Tavily-backed search provider for the DeepSeek Harness web capability seam (ctx.web): keyless mode, full official search parameters, settings section, and credentials support
Separator-transparent, abbreviation-aware slash-menu matching for the DeepSeek Harness web surface: provides the slashMatcher service the ui-commands and ui-skill sources consult, so `dshp` matches `dsh-plugin-creator` and `dbc` matches `dsh-better-command`.
Fixes malformed tool-call arguments (nested {"arguments":{…}} wrappers, wrapper-key aliases, param-key aliases) at the llm/stream seam — repairs execution, persistence and history replay in one place. 修复模型产出的畸形工具参数。
DeepSeek Harness bundle: a bounded, de-confounded hyperparameter sweep ledger with a research-campaign playbook skill and paper-ready report tables
A generic provider-dispatcher proxy for DeepSeek Harness. Mounts child plugins under a private isolate realm, records every register* call, and fans one operation out to all recorded children with a configurable strategy (parallel merge / race / bail).
Ships a skill that tells the agent when to delegate work to subagents instead of doing it inline, how to fan several out in parallel, and how to check what they returned.