Anthropic just shipped an OpenClaw killer called Claude Code Channels, which allows you to send messages over Telegram and Discord.

The successful open source AI autonomous agent open claw Maybe Anthropic had just harassed him.

Today, Anthropic announced Claude Code Channels, a way to connect your own powerful Claude Code AI agent harness to a human user’s Discord or Telegram messaging apps, allowing you to send messages to Claude Code directly whenever you want while on the go and instruct him to write code for them. The official documentation is here.

This is not just a new user interface; It is a fundamental change in the way developers interact with AI agents, moving from a synchronous system. "ask and wait" model to an asynchronous and autonomous association. Previously, Claude Code users were stuck interacting with the agent harness in the Claude desktop app, terminal or supported developer environment, and the Claude mobile app through a somewhat unstable system (in my experience). interconnection configuration called Remote Control.

Anthropic now offers some of the same core features as OpenClaw that drove its rapid adoption among software developers and vibration coders following its November 2025 release by Austrian developer Peter Steinberger (who, ironically, originally called his project "a dam" in honor of Anthropic’s AI model, Claude, who initially drove it, until Anthropic sent you a cease and desist for possible trademark violations. Steinberger who since being hired by Anthropic’s rival OpenAI.)

Central to OpenClaw’s appeal was its ability to allow users to have a personal, persistent AI worker that they can message 24/7 whenever they want, via common messaging apps like iMessage, Slack, Telegram, WhatsApp, and Discord, and have their AI respond to them, not just to chat, but to do real work for them on its own, from writing, sending, and organizing emails and files to creating complete applications, apply for employment on behalf of the user, to Manage entire ongoing social marketing campaigns. When the AI completes a task, it can immediately alert the human user via their preferred messaging platform.

But OpenClaw also carried a high degree of security risk (since it could be given access to a user’s hard drive and file system, or other personal information, and go crazy) and difficulty for non-technical users, inspiring a wave of ramifications that promise greater ease and security, including nanoclaw, KiloClaw and the recently announced by Nvidia NemoClaw.

By giving Claude Code this same basic functionality (the ability for users to message it from the popular third-party apps Discord and Telegram, and to message them back when a task is complete), Anthropic has effectively countered the appeal of OpenClaw and offered something it doesn’t: the Anthropic brand with its commitment to AI safety and its out-of-the-box ease of use for less technically inclined users.

Technology: Model Context Protocol Bridge

At the center of this update is the open source Model Context Protocol (MCP). standard that Anthropic introduced in 2024. Think of MCP as a universal USB-C port for AI: it provides a standardized way for an AI model to connect to external data and tools. in the new "Channels" architecture, an MCP server acts as a bidirectional bridge.

When a developer starts a Claude Code session with the --channels mark, they are not just opening a chat; They are launching a voting service.

Using the Bun runtime, known for its extreme speed in executing JavaScript, Claude Code monitors specific plugins (currently Telegram and Discord).

When a message arrives, it is injected directly into the active session as a <channel> event. Claude can then use his internal tools to run code, run tests or fix bugs, and respond to the external platform using specialized software. reply tool.

The technical achievement here is perseverance. Unlike a standard web chat that expires, a Claude Code session can now run in a terminal in the background or on a persistent server (such as a VPS), waiting for a response. "whistle" to take action.

How to set up Claude Code Connectors on Telegram and Discord

Setting up these native connectors requires Claude Code v2.1.80 or later and the Bun runtime installed on your desktop PC or Mac. Follow the instructions here or below.

1. Configure Telegram

Create your Bot: Open BotParent on Telegram and use the /newbot command to generate a unique bot and access token.
Install the plugin: Inside your Claude Code terminal, run: /plugin install telegram@claude-plugins-official
Configure the token: Run /telegram:configure <your-token> to save your credentials.
Reboot with channels: Exit Claude and restart using the channel flag: claude --channels plugin:telegram@claude-plugins-official
Match your account: Text your new bot on Telegram to receive a pairing code, then enter it into your terminal: /telegram:access pair <code>

2. Set up discord

Create an application: Go to the Discord Developer Portal, create a "new app," and reset the bot token to copy it.
Enable intents: In the Bot settings, you has to allow Intent of message content low "Privileged gateway intents."
Install and configure: In Claude Code, run /plugin install discord@claude-plugins-official followed by /discord:configure <your-token>.
Launch and match: Reboot with claude --channels plugin:discord@claude-plugins-official. Send a text message to your bot on Discord and use the /discord:access pair <code> command to end the link.

Product: From desktop to "everywhere"

The immediate practical impact is the democratization of mobile AI coding. Previously, if a developer wanted to check the status of a build or run a quick fix while away from their desk, they had to rely on complex self-hosted setups like OpenClaw.

With Channels, the configuration is native. A developer can create a Telegram bot through BotFather, link it to Claude Code with a /telegram:configure command, and "pair" your account with a security code. Once configured, the phone becomes a remote control for the development environment.

The product also introduces a "fake chat" Demo: A local-only chat UI that allows developers to test the "push" logic on your own machine before connecting to external servers. This reflects the cautious attitude and "research preview" approach, ensuring that developers understand the flow of events before exposing their endpoint to the Internet.

Licensing: ownership power over open standards

The licensing implications of this release highlight a growing trend in the AI industry: proprietary engines running in open tracks. Claude Code remains a proprietary product tied to Anthropic’s commercial subscriptions (Pro, Max and Enterprise).

However, by building on the open source model context protocol, Anthropic is fostering an ecosystem of developers to build the "connectors" which make your model more useful.

While the core Claude "brain" is closed, plugins for Telegram and Discord are hosted on GitHub in the official Anthropic repositories, likely allowing for community contributions or forks.

This strategy allows Anthropic to maintain model security and quality while benefiting from the rapid innovation of the open source community, a direct challenge to the "free" but often fragmented from purely open source agent frameworks.

And since it is built on MCP, the community can now build "Connectors" for Slack or WhatsApp, rather than waiting for Anthropic to send them.

Community Reactions: ‘The OpenClaw Killer’

The response from users, especially AI observers on X, was quick and definitive. The sentiment was best captured by Ejaaz (@cryptopunk7213)who noted that Anthropic’s shipping speed (incorporating text messaging, thousands of MCP skills, and autonomous error correction in just four weeks) was "fucking crazy."

For many, this update makes local agent frameworks obsolete. BentoBoi (@BentoBoiNFT) observed, "Claude just killed OpenClaw with this update. You no longer need to buy a Mac Mini. I say this as someone who owns one hahaha," referring to the common practice of developers purchasing dedicated hardware to run open source agents like OpenClaw 24/7. By transferring this persistence to the Claude Code environment, Anthropic has simplified the "hardware tax" for autonomy.

AI YouTuber Matthew Berman summed up the change succinctly: "They have BUILT OpenClaw."

The consensus among early adopters is that Anthropic has successfully internalized the most desirable features of the open source movement (multi-channel support and long-term memory) while maintaining the reliability of a top-tier AI vendor.

While Anthropic’s Claude has long been a favorite for his reasoning, he remained a "brain in a jar"—a stateless entity that waited for a user to type before it could think. Meanwhile, open source projects like OpenClaw thrived by offering "always active" persistence, allowing developers to send messages to their AI from Telegram or Discord to trigger complex workflows.

Now, with Anthropic closing the gap, it’s up to users to choose which approach is best for them.

Source link