Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

DeepSeek Harness plugin: per-edit approval with a red/green line diff before write/edit/str_replace_editor — approve once or reject (Claude Code behavior).

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

📟 Claude Code physical companion on M5Paper V1.1 e-ink. Multi-session dashboard, hardware approval (buttons + touch), AskUserQuestion option cards, CJK, USB/BLE, installable as a Claude Code plugin. / Claude Code 实体搭档，把 M5Paper 变成 Claude Code 的多会话看板 + 硬件审批面板。

Unified notification push plugin for DeepSeek Harness (DSH): one minimal notify() API, 8 channel adapters (telegram/dingtalk/feishu/wxpusher/pushplus/serverchan/bark/webhook), dual trigger (auto session events + agent tool).

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Catch up on Slack without reading it. Unreads, threads, search. Browser-session or hosted OAuth.

为 DSH 增加桌面通知提醒

DeepSeek Harness 权限规则引擎：hard/deny/ask/allow 四级规则（hard 高于全访问）、全局与 workspace 作用域、通配符路径保护、可视化草稿式编辑器，规则持久化于 settings.yaml

DSH Remote · 口袋里的 DSH 控制台 会话 · 审批 · 提问 · 文件传输，局域网 / Tailscale 直连 多服务器自动选优，聊天记录离线可看 带 Token 鉴权，数据只在你的设备之间流动 Sessions · approvals · questions · file transfer over LAN / Tailscale. Automatic fastest-server selection. Chat history available offline. Token-authenticated — your data flows only between your devices.

MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).

A pixel-art whale desktop companion for DeepSeek Harness — it swims while your agents work and taps the glass when an approval is waiting.

SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.

The Feishu UI for DeepSeek Harness — a panel-driven control console: every slash command a button on the ⚙️ control-panel card, in-card approvals & questions, live streaming cards, one-QR setup. | DeepSeek Harness 的飞书 UI：面板驱动控制台——每个命令都是卡片按钮，卡内审批与提问，流式卡片，扫码一键配置。

Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance

Agentic SEO operating system as a Claude Code plugin: project Wiki, DataForSEO workflows, content briefs, technical SEO, and human-approval gates.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Give your AI agent a spending limit: approval controls and single-use virtual cards.

Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions

🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.

Enables MCP clients to run project-scoped video editing workflows: propose and approve editing strategies, apply validated plans, review immutable versions, and export final renders via FFmpeg, with durable persistence and approval gates.