DIYgod releases Pinky — an MCP protocol layer for controlling real iPhone and Android AI agents
Read more
Pandaily
pandaily.com

DIYgod releases Pinky — an MCP protocol layer for controlling real iPhone and Android AI agents

Developer DIYgod has made the Pinky project available, a desktop application that allows artificial intelligence agents engaged in coding and general tasks to control real iPhone or Android devices via the Model Context Protocol (MCP). The user monitors the process and has the ability to approve or block potentially risky actions.

The repository on GitHub, released under the Apache-2.0 license, was created on November 6th. According to a Chinese AI publication reported in Tencent News, the post about this project garnered around 220,000 views on X, and the project received over 1000 stars on GitHub within the first 25 hours. By November 11th, GitHub had noted approximately 1700 stars, and the publication reported the release of 30 updates in a single day.

The Pinky application functions on macOS, Windows, and Linux operating systems. The README file states that it supports Android versions from 10 to 17 and iPhones on iOS 17.4 or later versions, requiring the installation of a helper component via Xcode for iOS 17.4–26. MCP-compatible agents include Claude Code, Claude Desktop, Codex, and Cursor, as well as any other tools or scripts supporting MCP. Pinky itself does not contain its own model and acts as a bridge between the agent and the phone.

Android devices can connect via Wi-Fi after initial cable connection. Starting with Android 13, Pinky uses a hidden second screen, allowing the agent to work while the phone's display remains locked. In the case of iOS, the agent gains access to the main phone screen. An additional Tailscale option provides access to Android phones outside the local network. Developers can also allow the agent to install custom APK files, read logs and crash reports, and then retest.

The main advantage is the thoughtful security system. The approval process is controlled by the Pinky gateway, not by instructions given to the agent. By default, payments, transfers, and purchases require manual confirmation by the user; users can add messages, make calls, delete data, and install applications. Banks, wallets, and password managers are hidden from the agent by default, and fields for entering passwords and one-time codes cannot be filled. Every action is recorded with a description, screenshot, and recording, and the session can be exported as an HTML report. The user can take control at any time, which will pause the agent's operation.

During testing conducted by the publication, the agent was able to publish a short video on a video application in approximately four minutes. The README states that screenshots and history are stored on the computer for 30 days, while anonymous usage statistics and crash reports are transmitted. A warning was also issued that some applications detect automation, and users should adhere to platform rules.

Similar stories

Alibaba introduces Qianwen Office 2.0 with AI agents for teamwork and event tasks
Read more
pandaily.com

Alibaba introduces Qianwen Office 2.0 with AI agents for teamwork and event tasks

Alibaba's workplace platform, DingTalk, released Qianwen Office 2.0 on November 9. This version features a 'Team Agent' for individuals and organizations, rather than just a single-user assistant. The company states that all functions are now available in the Qianwen Office client and calls this the most significant product update since its launch about three months ago.

The main feature is the 'Collaboration' function, which, according to DingTalk, is the first to support joint work among multiple people and an agent. A team creates a shared workspace for a project and receives a dedicated 'digital employee.' This space can link DingTalk group chats, AI documents, spreadsheets, and meeting notes, perform several parallel dialogues, and allow participants to assign tasks that the digital employee converts into progress summaries and subsequent tasks.

Product documentation specifies that a regular group member requires approval from the group administrator to link a chat.

Event-based task automation

The 'Automated Tasks' feature expands upon the old task scheduling capability by adding event-based triggers. Users can subscribe to specific events and set rules, after which the agent begins working when the specified conditions are met. The initial triggers include messages from a specified person, messages where the user is mentioned via @ in a specific group, and approval requests; the release notes also list other tasks.

One example in the release notes shows how a manager's message automatically creates a task in DingTalk.

Human-AI co-creation

The 'human-AI co-creation' mode allows users to open DingTalk documents, AI spreadsheets, or low-code Yida applications within a task dialogue. They can select paragraphs, cells, or slides, mark multiple comments, and send them simultaneously, after which the AI edits the original in place. DingTalk claims that multiple people and agents can co-edit content at the same time. The new resource space collects generated and uploaded files, and the mobile application allows initiating tasks and remotely controlling the assigned computer. The company reports that cloud tasks continue to run even after the computer is turned off.

A DingTalk use case demonstrates a team working with maps and coupons at Intime Department Store. Five employees previously compiled reports from over 60 store group chats and manually entered them into a spreadsheet. After connecting the chats and one spreadsheet to the shared space, the agent independently gathers information and updates the table. This case is an internal company example and did not record a measurable time reduction.

Information regarding pricing, number of users, and independent accuracy testing of the agent in general workspaces was not disclosed. According to the release notes, enterprise administrators have the option to disable the remote control feature.

openJiuwen's Hyper-Agent Swarm embeds persistent AI agents into work chats as digital employees
Read more
pandaily.com

openJiuwen's Hyper-Agent Swarm embeds persistent AI agents into work chats as digital employees

openJiuwen, an open agent community supported by Huawei, has released Hyper-Agent—a swarm architecture that moves agents from isolated chat sessions into real group work chats, transforming them into permanent digital employees. This was reported by IT Home as part of the community's publication.

The functionality is available in openJiuwen WorkSwarm, whose code is open-sourced on GitHub under the name JiuwenSwarm. The main change lies in altering the principle of agent connection to sessions. Instead of an agent being tied to a single conversation, the Persistent Agent retains its identity and state, continuously performing tasks while sessions become a base resource that the system distributes, schedules in parallel, and resumes while preserving context.

The system includes a gateway connecting instant messaging applications and a web interface, along with an AgentServer responsible for planning agents and work sessions. According to the community, this development builds upon previous work on Persistent Sessions and allows one agent to perform multiple tasks across various third-party group chats.

In WorkSwarm, users create these agents through an employee center, using either ready-made expert templates or creating them from scratch. When configuring, responsibilities, working style, delivery requirements, skills, connectors, knowledge sources, and even a dedicated email address are specified. When the context window approaches its limit, the agent switches to a new one, passing a summary of goals, progress, and next steps, and retrieves archived history if necessary.

There are two operating modes: passive mode only responds when mentioned, and adaptive mode decides whether to ignore a message, reply, or intervene based on its role and the flow of the conversation. An activity panel displays each agent's activity, token usage, and recent response time.

The same agent can operate in office applications such as Feishu and DingTalk, accepting a request in one channel and providing the result in another. Approval is required for information exchange between groups: users verify the source group, the recipient, and the content, after which they grant permission once or permanently, which can be revoked later.

Team members can also run WorkSwarm on their own devices, allowing agents on cloud servers and personal PCs to collaborate in the same group using locally authorized files and tools.

For larger projects, WorkSwarm utilizes the SwarmEngine group chat, which unites users, persistent agents, individual experts, and expert teams in one space. The expert team has a leader who takes tasks, reports progress, and organizes deliverables, while team members work in the background. Experts can be drawn from third-party agents like Codex and Claude Code and mixed with internal digital employees.

The community notes that future plans include the possibility of coordinating personal and cluster computing resources, active learning, and failure recovery to ensure longer-term collaboration.

DingTalk opens source code for DWS command-line tool for AI agents with HarmonyOS PC support
Read more
pandaily.com

DingTalk opens source code for DWS command-line tool for AI agents with HarmonyOS PC support

The Alibaba DingTalk working platform has made the DingTalk Workspace command-line tool, named DWS, publicly available, and has also released a version compatible with Huawei's HarmonyOS PCs. This project is hosted on GitHub under the Apache 2.0 license and is positioned as a command-line interface for DingTalk Workspace, developed for both users and artificial intelligence.

According to IT Home, DWS includes 25 business modules and over a thousand commands. The documentation lists services such as contact, chat, and group management, calendar events and meeting rooms, to-do lists, approvals, attendance records, work reports, AI tables, documents, whiteboards, cloud storage, AI meeting minutes, and email. The main idea is that the user describes the required task, and the agent performs it using these commands within the granted permissions, instead of the user having to manually switch between messages and tasks.

Agent application is the central goal of the design. Commands return structured data in JSON format, and the tool comes with built-in agent skills that can be installed individually for each product or as a single comprehensive skill. The documentation recommends using the confirmation skip flag for agents, the test run option for previewing a request without actually executing it, and a filter to extract only necessary fields so that agents consume fewer tokens.

Since DWS interacts with corporate data, administrator authorization from the enterprise is currently required. The project provides for login via OAuth device-flow, encrypted token storage tied to the device, a list of allowed domains that defaults to directing credentials only to DingTalk domains, use of HTTPS, and protective mechanisms preventing agents from being tricked by malicious input, such as path bypass and Unicode substitution filters. DingTalk states that every call passes through an open platform authentication and audit chain.

HarmonyOS PC support is implemented through the OpenHarmony build. The repository generates an openharmony/arm64 binary file using the OpenHarmony Go toolchain, and now every beta and stable version is compiled, self-signed, verified, and published along with six other platform archives. The project confirms that the binary file has been tested on HarmonyOS PCs. However, some features are unavailable in this build, including SafeChat and native runtime plugins.

IT Home notes that this is the first open command-line tool for office tasks on HarmonyOS PCs, filling a software gap for productivity enhancement on the Huawei desktop platform.

Popular