opencode VS clawdbot

Dax, the creator of OpenCode — an open-source coding agent, of all the people one might expect to disagree — put the case for hand-coding cleanly in a recent interview about Spec-Driven Development:

Pipa is our agent for studio operations at Lunch Pail Labs. She lives in Slack, is powered by E2B sandboxes, and uses OpenCode for the harness.

One reason I liked OpenSpec more than others, such as Kiro and SpecKit, is that OpenSpec is highly portable between coding assistants, codebases and stages of development. I've plugged OpenSpec into all sorts of projects, from infrastructure to Python libraries. I also work on diverse codebases, with a variety of AI friends that OpenSpec supports: OpenCode, Codex and Claude Code.

Beyond the big names, I would also keep an eye on OpenCode and T3 Code. OpenCode is a solid open-source, terminal-first option if you want a model-agnostic agent and bring your own provider setup. T3 Code is interesting for the opposite reason: it gives you an open-source GUI on top of the agents you may already pay for, like Claude Code, Codex CLI, OpenCode, or Cursor.

Brought to you by the infamous creator of OpenCode, who will exfiltrate all your data, then feign ignorance:

https://github.com/anomalyco/opencode/issues/10416

GitHub

I run an open-source AI assistant called OpenClaw on my MacBook. It's a daemon that connects to Slack, Telegram, WhatsApp — basically any messaging platform — and runs Claude as a persistent, autonomous agent on your machine.

Official GitHub SECURITY.md

- Pass a WebSocket URL → chat input appears, face reacts to responses in real-time

The face is a single self-contained JS file (face.js, ~17KB) that injects its own SVG, CSS, and animation loop. Natural blinking, pupil drift, breathing animation, ambient glow, and a subtitle system — all pure JS/SVG, no canvas, no WebGL, no React.

There's also a gateway integration module (clawdbot.js) that maps agent events to expressions automatically — thinking when processing, investigating when searching the web, working when running code, confused on errors.

Built for Clawdbot (https://github.com/clawdbot/clawdbot) and Moltbot (https://github.com/moltbot/moltbot), but face.js works standalone with anything. Just call face.set('happy', 5000).

Zero npm install. Zero bundler. Copy the file, add the script tag, done.

Check the GitHub repo for issues and code

I've been running Clawdbot, a persistent AI assistant, for a few days (yeah only days) now. It reads my email, manages my calendar, browses the web on my behalf, and remembers conversations across sessions. It does everything my current VA does. It's changed how I think about software design. Clawd has no interface, no web page for interaction, nothing... and the absence of a traditional interface hasn't diminished the experience. If anything, it's clarified something we've been dancing around since agents have started to take shape: most interface design exists to compensate for computers not understanding what users want.

mkdir -p ~/GIT/clawdbot-project cd ~/GIT/clawdbot-project git clone https://github.com/clawdbot/clawdbot.git cd clawdbot ./docker-setup.sh

Last weekend, I stumbled onto something called Clawdbot. It's basically a self-hosted AI assistant that you can chat with through Discord, Slack, or even WhatsApp. Cool, but I wasn't sure what I'd actually use it for.