Skip to main content
Published in Engineering Insights

Anthropic Dropped OpenClaw Support. Here's How I Replaced It With Claude Code.

Anthropic Dropped OpenClaw Support. Here's How I Replaced It With Claude Code.
Table of contents
  1. The Economics Problem
  2. ClawChat: The Client That Made This Possible
  3. Setting up the Discord channel, step by step
  4. Claude Code Channels as a Drop-In Backend
  5. What a Claude Code channel is, and its status today
  6. Trying a channel first with fakechat
  7. What the development flag does and what a channel server must do
  8. Adding Claude Support to ClawChat
  9. Migrating the Configuration
  10. Honest Assessment

Anthropic recently changed their Terms of Service, effectively killing OpenClaw. This wasn't a gradual sunsetting or a slow loss of momentum. The project was active and the community was thriving. It stopped abruptly because of a policy change. I believe this is the end of OpenClaw as we know it, and it leaves a lot of users figuring out what comes next.

I was one of those users. As co-founder of The Gnar, I don't get to focus as much on IC work anymore. So when I do get to write code, it's usually on internal tools or side projects. OpenClaw had become a big part of that. Home automation, side project scripting, general tinkering. I was an early adopter and had invested real time getting it stable enough to use as a daily driver.

The catch: I never trusted it enough to run on my work machine. It always lived in an isolated Docker container in my home lab (named Pinchy, naturally) where it could operate without me worrying about what it had access to. That security-first instinct turned out to be useful when it came time to migrate.

The Economics Problem#

With the TOS change, running OpenClaw going forward means doing it without Anthropic's support. And the economics of that aren't pretty. Running it via API calls is prohibitively expensive, and using an alternative backend like Gemini is still very costly for what amounts to a personal assistant. The long-term viability just isn't there.

At work, I rely on Claude and have been impressed by the progress Anthropic has been making toward more autonomous agents and the tooling around them. So the natural question was: could Claude Code replicate the isolated, containerized assistant experience I had with OpenClaw?

ClawChat: The Client That Made This Possible#

Some context on my setup. Most people interacted with OpenClaw through Discord or other community channels. I'm old and don't have Discord friends, so I built ClawChat, an Electron app (React + TypeScript, built with Vite) that handled about 95% of my OpenClaw interactions.

ClawChat connects to backends over WebSocket, handles the Ed25519 crypto handshake for OpenClaw's gateway protocol, supports streaming deltas, and stores credentials locally via electron-store. It has SSH tunneling for remote connections and all the slash commands you'd expect. Nothing groundbreaking, but it was purpose-built for how I actually wanted to use an AI assistant: from a dedicated desktop app, not a chat platform.

Having this abstraction layer between me and the backend turned out to be the key to a smooth migration. The client didn't care what was on the other end of the WebSocket. It just needed to send messages and receive responses.

Setting up the Discord channel, step by step#

You set up an official Discord channel by making a bot, installing a plugin, and pairing your account. Anthropic's channels page, read on November 15, 2026, lists the steps. The post says: "Most people interacted with OpenClaw through Discord or other community channels." The post's own setup connects ClawChat through its own MCP channel server, described below. Before step 1, the page says: "Each supported channel is a plugin that requires Bun."

  1. Create the bot. The page says to "click New Application, and name it". In the Bot section, it says to "create a username, then click Reset Token and copy the token".
  2. Turn on the intent. The page says to "enable Message Content Intent".
  3. Invite the bot. The page says to go to OAuth2 > URL Generator, pick the bot scope, and turn on six permissions: View Channels, Send Messages, Send Messages in Threads, Read Message History, Attach Files, and Add Reactions. Then it says to "Open the generated URL to add the bot to your server".
  4. Install the plugin with /plugin install discord@claude-plugins-official. The page says to "enter this at its prompt". It says to "Check the install summary". If the summary shows Run /reload-plugins to apply., follow its link "to make the plugin's configure command available".
  5. Save the token with /discord:configure <token>. The page adds that "You can also set DISCORD_BOT_TOKEN in your shell environment before launching Claude Code".
  6. Restart with claude --channels plugin:discord@claude-plugins-official. The page says this "connects the Discord plugin so your bot can receive and respond to messages".
  7. Pair your account with /discord:access pair <code>. First, "DM your bot on Discord. The bot replies with a pairing code".
  8. Lock access with /discord:access policy allowlist. The page says to "lock down access so only your account can send messages".

The page also says: "Every approved channel plugin maintains a sender allowlist: only IDs you've added can push messages, and everyone else is silently dropped."

Claude Code Channels as a Drop-In Backend#

Claude Code's new channels feature turned out to be exactly the bridge I needed. Channels let you communicate with a Claude Code instance programmatically through MCP (Model Context Protocol), which meant I could wire up ClawChat to talk to Claude Code the same way it talked to OpenClaw.

Here's the architecture:

A Docker container running node:22-slim with Claude Code installed, a workspace volume mounted, and port 9700 exposed. It needs a Claude Max subscription OAuth token (generated via claude setup-token) passed through a .env file.

An MCP channel server (server.mjs) that serves as the bridge:

  1. Connects to Claude Code over stdio using the channel capability
  2. Exposes a WebSocket server on port 9700 for ClawChat to connect to
  3. Translates between ClawChat's message protocol and MCP channel notifications

The server registers a send_reply tool that Claude uses to push responses back through the channel. The MCP config is minimal:

json

{
 "mcpServers": {
   "channel-test": {
     "command": "node",
     "args": ["/workspace/channel-test/server.mjs"],
     "env": { "CHANNEL_PORT": "9700" }
   }
 }
}

Claude Code launches with --dangerously-load-development-channels to enable the channel server. The flag name is a bit alarming, but channels are still in development preview.

The message flow: ClawChat sends a chat.send request -> channel server acknowledges with a runId -> forwards via MCP to Claude Code -> Claude calls send_reply -> server broadcasts as a chat event -> ClawChat renders the response.

What a Claude Code channel is, and its status today#

A channel is an MCP server that pushes events into a Claude Code session, and Anthropic's channels page calls the feature a "research preview". That channels page, read on November 15, 2026, says "A channel is an MCP server that pushes events into your running Claude Code session". The post above says: "Channels let you communicate with a Claude Code instance programmatically through MCP (Model Context Protocol)." The post calls this status a development preview.

TopicWhat Anthropic's channels pages say
Definition"A channel is an MCP server that pushes events into your running Claude Code session"
Status"Channels are in research preview"
What may change"protocol contract may change based on feedback"
Where it is not available"not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry"
Team and Enterprise"Team and Enterprise organizations must explicitly enable them"

The same page says "Telegram, Discord, and iMessage are included in the research preview". It describes fakechat as "an officially supported demo channel".

Trying a channel first with fakechat#

You try fakechat by installing its plugin, restarting Claude Code with the channels flag, and opening a local web page to type a message. The post says the ClawChat client "just needed to send messages and receive responses." The quickstart on Anthropic's channels page, read on November 15, 2026, says "you can type in the browser and the message arrives in your Claude Code session". It uses fakechat, "with nothing to authenticate and no external service to configure".

The page lists what you need first:

  • Bun, because "The pre-built channel plugins are Bun scripts."
  • Claude Code "installed and authenticated with a claude.ai account or a Claude Console API key".
  • The page says: "Team, Enterprise, or managed Console org: your admin must enable channels in managed settings".
  1. Install the plugin with /plugin install fakechat@claude-plugins-official. The page says to "choose the user scope option so the plugin is available across all your projects".
  2. Restart with claude --channels plugin:fakechat@claude-plugins-official. The page says "The fakechat server starts automatically."
  3. Open http://localhost:8787 and type a message. The page says "The message arrives in your Claude Code session."

What the development flag does and what a channel server must do#

The development flag lets Claude Code load a custom channel that is not on the approved allowlist, after a confirmation prompt. A channel server must declare a capability, send events and connect over stdio. Anthropic's channels reference, read on November 15, 2026, says the flag "bypasses the allowlist for specific entries after a confirmation prompt". The post says: "The flag name is a bit alarming, but channels are still in development preview."

Development flagWhat the reference says
Why a custom channel needs it"During the research preview, custom channels aren't on the approved allowlist"
Default allowlist"The default allowlist is the channel plugins in claude-plugins-official"
What it skips"This flag skips the allowlist only"
What you see on start"warning dialog listing the development channels you're loading"
With -p or the Agent SDK"Claude Code ignores the flag and the channel doesn't register"
Trust"Don't use it to run channels from untrusted sources"
Channel serverWhat the reference says
Declare a capability"Declare the claude/channel capability"
Send events"Emit notifications/claude/channel events when something happens"
Connect"Connect over stdio transport"
Delivery"Events queue into the session and are processed in order"
Acknowledgement"Claude Code doesn't acknowledge notifications"

Adding Claude Support to ClawChat#

On the client side, the changes were surprisingly minimal. PR #26 covers the full implementation. The main additions were a BackendType union type ('openclaw' | 'channel') threaded through the gateway client, hooks, and connection screen; a tabbed connect interface for switching between backends; separate credential storage for each; and bypassing the Ed25519 handshake for the channel path since MCP handles auth differently. All 12 existing tests passed, TypeScript compiled clean.

For anyone maintaining a similar client app that talks to OpenClaw, the pattern here is straightforward: abstract your transport layer, add a backend selector, and let the channel server handle the protocol translation.

Migrating the Configuration#

OpenClaw used a handful of markdown files to define its behavior: SOUL.md for personality and tone, plus config files for tool permissions, task patterns, and behavioral guardrails. Claude Code has its own equivalent: it reads a CLAUDE.md file automatically at the start of every session.

Rather than manually translating each file, I pointed Claude Code at the OpenClaw markdown files and had it do the analysis itself. It looked at what each file was doing, figured out the Claude Code equivalents, and consolidated everything into a single CLAUDE.md that made sense from a compatibility perspective. Some concepts mapped directly, others needed rethinking for how Claude Code handles tool access and autonomy levels, but the end result captured the spirit of my OpenClaw setup without hand-translating a bunch of config.

Honest Assessment#

This isn't a seamless replacement yet. There are real limitations: no streaming (responses arrive as a single event rather than incremental deltas), single conversation per instance, and a manual warning prompt to accept after each container restart.

But it works better than I expected as a daily driver for personal use. The responses are solid, the isolation model gives me the same security boundary I had with Pinchy, and I have access to all the new features Anthropic keeps shipping. I suspect that within the next few weeks, as channels matures, this setup will reach decent parity with how I used OpenClaw.

The TOS change hit different parts of the OpenClaw ecosystem very differently. Businesses that were built on top of it (tooling providers, hosting services, managed platforms) essentially evaporated overnight. That's a real cost and it's worth acknowledging. But for end users like me who were running OpenClaw as a personal tool, the story is more hopeful. Claude Code plus channels provides a viable path forward. It's not a one-to-one replacement, but it's a foundation that's actively improving and backed by a company that's investing heavily in this space.

The ClawChat repo has the Docker Compose config, channel server code, and setup docs. If you're comfortable running containers and wiring up WebSockets, the migration is more approachable than you might think.

Frequently asked questions

How does ClawChat talk to Claude Code?

An MCP channel server receives WebSocket messages from ClawChat and translates them into channel notifications. Claude uses send_reply to send responses back.

What does the container setup require?

The described setup uses node:22-slim, Claude Code, a mounted workspace volume and port 9700. A Claude Max subscription OAuth token generated with claude setup-token is passed through a .env file.

How was the old configuration migrated?

The author asked Claude Code to analyze the OpenClaw markdown files and consolidate them into CLAUDE.md. Some concepts mapped directly, while others needed changes for tool access and autonomy.

Does the replacement have limitations?

Yes. It lacks streaming, allows a single conversation per instance and requires a manual warning prompt after each container restart. The author found it useful as a personal daily driver despite those limits.

What is a Claude Code channel?

A channel is an MCP server that pushes events into a running Claude Code session, according to Anthropic's channels page. Anthropic puts channels in research preview and says the protocol contract may change based on feedback.

Which chat apps does Anthropic's channels feature support?

Anthropic's channels page says Telegram, Discord, and iMessage are included in the research preview. It also describes fakechat as an officially supported demo channel that runs a chat UI on localhost.

Stay In The Loop

Never miss an update. Get the latest blogs, webinars, and expert insights straight to your inbox from The Gnar.