Anthropic Launches Its Own OpenClaw‑Style Tools: Dispatch and Claude Code Channels

Anthropic, after suing the open‑source OpenClaw project, released its own official equivalents—Dispatch and Claude Code Channels—offering sandboxed, mobile‑controlled AI agents, integrated with Telegram and Discord, and the article details their functionality, setup steps, and compares them with the original OpenClaw’s strengths and limitations.

AI Insight Log
AI Insight Log
AI Insight Log
Anthropic Launches Its Own OpenClaw‑Style Tools: Dispatch and Claude Code Channels

Two months ago Anthropic sent a cease‑and‑desist letter to the open‑source project Clawdbot, forcing it to rename itself OpenClaw. The project then exploded, gaining 250,000 GitHub stars in 60 days and supporting over 50 chat platforms.

In a reversal, Anthropic announced on March 18 that it has built an “official” OpenClaw‑style product called Dispatch . Dispatch creates a persistent chat channel between a user’s phone and Claude running on the local computer, allowing the user to assign tasks on the PC and receive progress notifications.

Key details of Dispatch:

Sandboxed execution : all code runs locally; Claude must obtain user approval before each operation.

Mobile control : after pairing with the Claude Desktop app, commands can be sent from a phone.

Persistent session : the conversation remains active across windows, acting as a long‑running work session.

Dispatch was first opened to Max‑subscriber users on March 18 and covered 100% of Claude Pro users after one day. On March 19 Anthropic added support for Claude Code , enabling commands such as “refactor this function” or “run the tests” directly from the phone. The following day, March 20, Anthropic released Claude Code Channels , extending the same capability to third‑party messengers via the MCP protocol. The announcement tweet by engineer Thariq received 6.55 million views, highlighting strong community interest.

Telegram Channel setup (official plugin repository):

Create a bot on Telegram by messaging /newbot to @BotFather and obtain the token.

Install the Telegram plugin and configure the token:

# Install Telegram plugin
/plugin install telegram@claude-plugins-official

# Configure Bot Token
/telegram:configure YOUR_TOKEN

Start Channels mode:

claude --channels plugin:telegram@claude-plugins-official

Pair the bot by sending a message to it on Telegram, receiving a 6‑digit code, and entering it in Claude Code: /telegram:access pair CODE Optionally switch the access policy to whitelist to prevent unauthorized pairing: /telegram:access policy allowlist After configuration, Claude Code can receive commands via Telegram, send files up to 50 MB, react with emojis, and edit messages.

Comparison with OpenClaw:

Both share the core idea of using a chat interface to remotely control a local AI agent.

Both support Telegram and Discord.

Both emphasize local execution and data privacy.

Anthropic’s advantages:

Out‑of‑the‑box : no need to set up Docker or custom environments; Dispatch works with a Claude Desktop update, Channels require only a few commands.

Native integration : Dispatch and Claude Code are built by Anthropic, guaranteeing tighter stability.

Security design : sandboxed execution and explicit user approval, avoiding the early security issues reported in OpenClaw.

OpenClaw’s advantages:

Platform coverage : supports 50+ chat platforms, while Channels currently support only Telegram and Discord (though 15 external plugins are already available).

Model freedom : can run any LLM (GPT, DeepSeek, Llama, etc.) and mix “brain + muscle” architectures to reduce cost.

Rich ecosystem : a large community contributes Skills, plugins, and use‑cases such as daily reports, auto‑Vibe coding, and reverse prompts.

Maturity : months of large‑scale usage have produced a feature‑rich product compared with the newly launched Dispatch.

Anthropic’s strategic shift (timeline):

Nov 2025 – Clawdbot created, using Claude as the underlying model.

Jan 2026 – Anthropic sent a legal notice demanding a name change.

Feb 2026 – Anthropic blocked third‑party tools from using Claude Pro/Max OAuth tokens.

Mar 2026 – Anthropic released Dispatch and Claude Code Channels, mirroring OpenClaw’s functionality.

The company moved from a “block” strategy—legal threats and token bans—to a “build” strategy, recognizing that users genuinely want to control AI agents via chat. By providing an official, secure, and integrated solution, Anthropic aims to capture the demand that OpenClaw proved existed.

Original Source

Signed-in readers can open the original source through BestHub's protected redirect.

Sign in to view source
Republication Notice

This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactadmin@besthub.devand we will review it promptly.

AI agentsDispatchremote executionAnthropicOpenClawTelegram integrationClaude Code Channels
AI Insight Log
Written by

AI Insight Log

Focused on sharing: AI programming | Agents | Tools

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.