dsh-auto-review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
80 results
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
记忆核心(Memory Eternal):自研的 DeepSeek Harness 记忆插件,不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault(自研去重、自研 CJK 检索、可 git 管理),设置页提供图形化知识库(统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗),Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。
DSH-KRouter — Agent knowledge OS. Self-evolution. Timer on by default; your vault-page API key or logged-in CLI is the key. Cursor, Codex, Claude Code, DeepSeek Harness. No vector store.
Scientific writing & document integrity guard for AI-assisted research - prompt-guided argument economy with deterministic scientific, delivery, journal, and Word integrity checks.
Minimal Root-Orchestrator PTES pentesting plugin for DeepSeek Harness
A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 75 models from one credential: a BlockRun API key, or a wallet paying per call over x402.
DSH plugin exposing a single `sleep` tool that lets the model pause for a configurable number of milliseconds, honoring cancellation.
DeepSeek Harness plugin: secondary working directories for a project. The agent keeps the primary workspace as cwd, gains equal write/exec permissions on configured secondary directories under workspace-write mode, and is notified of configuration changes at the next message boundary. Configurable from the session header AND from the session-creation page (before the first message) through a sessionless multiFolder remote API.
dsh plugin (Windows): desktop shortcut that launches dsh web silently (hidden console) and auto-opens the browser; port-aware reconnect; settings UI section; tray with native toast notifications and close-to-exit semantics.
DSH SuperAdvisor: on-demand second opinions with manual, model-tag, independent AI or approve-all policies
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
Finance and accounting workflows for DeepSeek Harness, adapted from Anthropic's Finance plugin.
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
Clean desktop shell for DeepSeek Harness (DSH) as a DSH plugin — wraps your web profile in a native window, tray-managed backend, offline auto-reconnect, zero visual changes. DSH 插件形态的纯净桌面壳:复用现有 web profile,托盘管理后端,零视觉改造。
记忆核心(Memory Eternal):自研的 DeepSeek Harness 记忆插件,不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault(自研去重、自研 CJK 检索、可 git 管理),设置页提供图形化知识库(统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗),Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。
DeepSeek Harness plugin (Cordis toolset) for reading, searching, and editing a local Obsidian vault, with optional Local REST API integration.
Graceful restart + client auto-reconnect + cross-restart goal continuation for DeepSeek Harness (dsh). After a plugin update dsh-phoenix restarts dsh at a safe idle boundary, keeps the browser page connected, and resumes a running goal so a task can keep evolving across restarts.
SSH terminal panel and AI connection manager for DeepSeek Harness: model-driven SSH connections (connect/exec/list/status/disconnect), auto-saved connection records, keep-alive + auto-reconnect, execution mutex, credential-safe auth, and an XShell-style multi-tab terminal panel in the Web GUI.
站点地图(Yakit 风格):侧边栏树形接口地图(站点配色 + 一键清除)+ Cookie 保险库(JSON/Header/Netscape 导入、按域名自动标注覆盖站点)+ src 工作流工具(sitemap_query / sitemap_cookie / sitemap_regen / sitemap_import_cookie)。
Loom (织机) — second-validator plugin for DeepSeek Harness: a silent external coach that weaves your agent's tools, skills, config and even its model from usage history, with deterministic verification and cold-apply.
Weak-network adaptor for the DeepSeek Harness: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, degraded-mode token economy, and a bilingual (zh/en) settings page. / 弱网适配插件:模型流长退避重试、本地响应缓存、心跳自动重连(默认 10 分钟封顶)、降级省 token、双语设置页。
让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy,运行中新增的 provider 也会自动补上,再也不用手动发「继续」。
team-task for DeepSeek Harness: long-horizon multi-agent tasks — a lead plans a reviewed DAG, durable members execute, an event log is the single truth, and a resident reconciler survives crashes and restarts.
Safe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits.