不把整台机器交出去，只送出挡路的决定和下一步：DeepSeek Harness 的审批、ask_user_question 提问与结果回复，以飞书卡片发到手机——桌面优先、只出站；执行过程实时可见，下一段任务一键即开。

Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.

A gateway between AI agents and Postgres: table access, masking at the source, approvals and audit.

Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.

Founders' AI COO: every AI cofounder's Routines on time — heartbeat, failures, approvals, reports.

66 public tools: semantic search, queues, inboxes, webhooks, approvals, DNS, images, PDF and more.

Self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.

DSH plugin: connect WeChat (official iLink/ClawBot) to DeepSeek Harness — settings page with live bridge status, QR device pairing, in-WeChat tool approvals, proactive push, and the bundled bridge + keeper kernel.

Let Claude, ChatGPT or Cursor manage your servers, sites and SEO, with approvals for risky actions.

Enables AI assistants to operate Shopify stores through 61 risk-tiered tools for store operations, SEO and GEO audits, deterministic analytics, inventory intelligence, feed quality, and safe marketing workflows. It defaults to read-only access and uses previews, bound approvals, and audit logging for writes.

Enables an MCP-capable AI chat to control selected tabs in a separate persistent Chromium browser, protected by OAuth, per-tab grants, and local approvals.

Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.

Enables MCP clients such as Claude to query mail, schedules, and electronic approvals, reserve meeting rooms, and manage personal schedules through a groupware account.

Enables any AI agent to work inside your own signed-in Chrome or Edge, with risky steps gated behind approvals the agent cannot skip, receipts for every action, routines that replay without the AI, and per-site packs that read a site's own data. Everything runs locally, so pages, cookies and passwords never leave your machine.

Android companion for DeepSeek Harness | chat, goals, approvals & notifications from your phone, over your LAN. Kotlin + Jetpack Compose.

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Codex · GLM).

Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.

Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.

Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.

Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.

Sovereign AI agents for business: answers from company data, each person's permissions, approvals.

Paid x402 crypto safety tools (Base/ETH/BSC): tx, approvals, contract risk, token deep scan.

Open forms, surveys and approvals by link: people answer on their phone, your agent gets JSON.

Run every client's AI from one console: workspaces, roles, MCP tools, approvals and spend.