DEV Community: 0xkoji

Supply Chain Security measures

0xkoji — Fri, 03 Apr 2026 23:35:46 +0000

6 Must-know commands for cleaning up Homebrew packages

0xkoji — Fri, 20 Mar 2026 10:51:46 +0000

I recently discovered "zerobrew" and decided to switch over from Homebrew. To prepare for the transition, I've been cleaning up my Homebrew packages using these commands.

Since zerobrew doesn't support every package available on Homebrew yet (for example, "Codex"), I'm currently running both side-by-side.

zb install codex
==> Installing codex...

Note: This package can't be installed with zerobrew.
      Error: missing formula 'codex'

      Try installing with Homebrew instead:
      brew install codex

error: missing formula 'codex'
Execution time: 0.94s

zerobrew

zerobrew brings uv-style architecture to Homebrew packages on macOS and Linux.

Install

curl -fsSL https://zerobrew.rs/install | bash

After install, run the export command it prints (or restart your terminal).

Quick start

zb install jq                   # install one package
zb install wget git             # install multiple
zb bundle                       # install from Brewfile
zb bundle install -f myfile     # install from custom file
zb bundle dump                  # export installed packages to Brewfile
zb bundle dump -f out --force   # dump to custom file (overwrite)
zb uninstall jq                 # uninstall one package
zb reset                        # uninstall everything
zb gc                           # garbage collect unused store entries
zbx jq --version                # run without linking

Performance snapshot

Package	Homebrew	ZB (cold)	ZB (warm)	Cold Speedup	Warm Speedup
Overall (top 100)	452s	226s	59s	2.0x	7.6x
ffmpeg	3034ms	3481ms	688ms	0.9x	4.4x
libsodium	2353ms	392ms	130ms	6.0x	18.1x
sqlite	2876ms	625ms	159ms	4.6x	18.1x
tesseract	18950ms

…

View on GitHub

`brew leaves`

Show packages that are not dependencies of other packages.

`brew autoremove`

Remove unused dependencies that are no longer needed.

`brew doctor`

To diagnose and fix potential issues in my setup.

`brew cleanup`

Remove stale lock files and outdated downloads.

Usage: brew cleanup [options] [formula|cask ...]

Remove stale lock files and outdated downloads for all formulae and casks, and
remove old versions of installed formulae. If arguments are specified, only do
this for the given formulae and casks. Removes all downloads more than 120 days
old. This can be adjusted with $HOMEBREW_CLEANUP_MAX_AGE_DAYS.

      --prune                      Remove all cache files older than specified
                                   days. If you want to remove everything, use
                                   --prune=all.
  -n, --dry-run                    Show what would be removed, but do not
                                   actually remove anything.
  -s, --scrub                      Scrub the cache, including downloads for even
                                   the latest versions. Note that downloads for
                                   any installed formulae or casks will still
                                   not be deleted. If you want to delete those
                                   too: rm -rf "$(brew --cache)"
      --prune-prefix               Only prune the symlinks and directories from
                                   the prefix and remove no other files.
  -d, --debug                      Display any debugging information.
  -q, --quiet                      Make some output more quiet.
  -v, --verbose                    Make some output more verbose.
  -h, --help                       Show this message.

`brew bundle dump`

Create a Brewfile to snapshot your current setup.

`brew bundle --force cleanup`

Uninstall everything not listed in your Brewfile.

I have used the alias, brew_all

.zshrc

alias brew_all="brew outdated && brew update && brew upgrade && brew cleanup -s"

A Quick Look at Claw-Family

0xkoji — Mon, 16 Mar 2026 05:23:46 +0000

OpenClaw

🦞 OpenClaw — Personal AI Assistant

EXFOLIATE! EXFOLIATE!

OpenClaw is a personal AI assistant you run on your own devices It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WebChat). It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.

If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.

Website · Docs · Vision · DeepWiki · Getting Started · Updating · Showcase · FAQ · Onboarding · Nix · Docker · Discord

Preferred setup: run openclaw onboard in your terminal OpenClaw Onboard guides you step by step through setting up the gateway, workspace, channels, and skills. It is…

View on GitHub

I tried using OpenClaw, but I had some concerns about its security. So I decided to do a bit of research to see if there were any alternative options.
I'm testing zeroclaw now 💪

HiClaw

alibaba / hiclaw

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

English | 中文

HiClaw is an open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

Built with a Manager-Workers architecture, HiClaw lets you coordinate multiple Worker Agents through a Manager Agent to complete complex tasks — all conversations are visible in Matrix rooms, and you can intervene at any time.

Think of it as your AI team in a chat room: tell the Manager what you need, it spins up Workers, and you watch everything happen in real-time.

Key Features

🧬 Manager-Workers Architecture: Eliminates the need for human oversight of individual Worker Claws by enabling Agents to manage other Agents.
🦞 Customizable Agents: Each Agent supports flexible configurations including OpenClaw, Copaw, NanoClaw, ZeroClaw, and enterprise-built Agents—scaling from individual "shrimp farming" to full-scale "shrimp farm" operations..
📦 MinIO Shared File System: Introduces a shared file system for inter-Agent information exchange, significantly reducing token consumption…

View on GitHub

overview

HiClaw is an open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

NemoClaw

NVIDIA / NemoClaw

Run OpenClaw securely inside NVIDIA OpenShell with managed inference

NVIDIA NemoClaw: Reference Stack for Running OpenClaw in OpenShell

NVIDIA NemoClaw is an open source reference stack that simplifies running OpenClaw always-on assistants more safely. It installs the NVIDIA OpenShell runtime, part of NVIDIA Agent Toolkit, which provides additional security for running autonomous agents. It also includes open source models such as NVIDIA Nemotron.

Alpha software

NemoClaw is available in early preview starting March 16, 2026. This software is not production-ready. Interfaces, APIs, and behavior may change without notice as we iterate on the design. The project is shared to gather feedback and enable early experimentation. We welcome issues and discussion from the community while the project evolves.

Quick Start

Follow these steps to get started with NemoClaw and your first sandboxed OpenClaw agent.

ℹ️ Note

NemoClaw creates a fresh OpenClaw instance inside the sandbox during onboarding.

Prerequisites

Check the prerequisites before you start to ensure you have the…

View on GitHub

overview

NVIDIA NemoClaw is an open source stack that simplifies running OpenClaw always-on assistants safely. It installs the NVIDIA OpenShell runtime, part of NVIDIA Agent Toolkit, a secure environment for running autonomous agents, with inference routed through NVIDIA cloud.

picoclaw

sipeed / picoclaw

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

PicoClaw: Ultra-Efficient AI Assistant in Go

$10 Hardware · <10MB RAM · <1s Boot · 皮皮虾，我们走！

PicoClaw is an independent open-source project initiated by Sipeed. It is written entirely in Go — not a fork of OpenClaw, NanoBot, or any other project.

🦐 PicoClaw is an ultra-lightweight personal AI Assistant inspired by NanoBot, refactored from the ground up in Go through a self-bootstrapping process, where the AI agent itself drove the entire architectural migration and code optimization.

⚡️ Runs on $10 hardware with <10MB RAM: That's 99% less memory than OpenClaw and 98% cheaper than a Mac mini!

Caution

🚨 SECURITY & OFFICIAL CHANNELS / 安全声明

NO CRYPTO: PicoClaw has NO official token/coin. All claims on pump.fun or other trading platforms are SCAMS.
OFFICIAL DOMAIN: The ONLY official website is…

View on GitHub

overview

🦐 PicoClaw is an ultra-lightweight personal AI Assistant inspired by nanobot, refactored from the ground up in Go through a self-bootstrapping process, where the AI agent itself drove the entire architectural migration and code optimization.

nanoclaw

qwibitai / nanoclaw

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

An AI assistant that runs agents securely in their own containers. Lightweight, built to be easily understood and completely customized for your needs

nanoclaw.dev • 中文 • 日本語 • •

🐳 Now Runs in Docker Sandboxes

Every agent gets its own isolated container inside a micro VM.
Hypervisor-level isolation. Millisecond startup. No complex setup.

macOS (Apple Silicon)

curl -fsSL https://nanoclaw.dev/install-docker-sandboxes.sh | bash

Windows (WSL)

curl -fsSL https://nanoclaw.dev/install-docker-sandboxes-windows.sh | bash

Currently supported on macOS (Apple Silicon) and Windows (x86). Linux support coming soon.

Read the announcement → · Manual setup guide →

Why I Built NanoClaw

OpenClaw is an impressive project, but I wouldn't have been able to sleep if I had given complex software I didn't understand full access to my life. OpenClaw has nearly half a million lines of code, 53 config files, and 70+ dependencies. Its security is at the application level (allowlists, pairing codes) rather than true…

View on GitHub

overview

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK.

zeroclaw

zeroclaw-labs / zeroclaw

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

🦀 ZeroClaw — Personal AI Assistant

Zero overhead. Zero compromise. 100% Rust. 100% Agnostic.
⚡️ Runs on $10 hardware with <5MB RAM: That's 99% less memory than OpenClaw and 98% cheaper than a Mac mini!

Built by students and members of the Harvard, MIT, and Sundai.Club communities

🌐 Languages: 🇺🇸 English · 🇨🇳 简体中文 · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇻🇳 Tiếng Việt · 🇵🇭 Tagalog · 🇪🇸 Español · 🇧🇷 Português · 🇮🇹 Italiano · 🇩🇪 Deutsch · 🇫🇷 Français · 🇸🇦 العربية · 🇮🇳 हिन्दी · 🇷🇺 Русский · 🇧🇩 বাংলা · 🇮🇱 עברית · 🇵🇱 Polski · 🇨🇿 Čeština · 🇳🇱 Nederlands · 🇹🇷 Türkçe · 🇺🇦 Українська · 🇮🇩 Bahasa Indonesia · 🇹🇭 ไทย · 🇵🇰 اردو · 🇷🇴 Română · 🇸🇪 Svenska · 🇬🇷 Ελληνικά · 🇭🇺 Magyar · 🇫🇮 Suomi · 🇩🇰 Dansk · 🇳🇴 Norsk

ZeroClaw is a personal AI assistant you…

View on GitHub

overview

Fast, small, and fully autonomous AI assistant infrastructure — deploy anywhere, swap anything 🦀

nanobot

HKUDS / nanobot

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

nanobot: Ultra-Lightweight Personal AI Assistant

🐈 nanobot is an ultra-lightweight personal AI assistant inspired by OpenClaw.

⚡️ Delivers core agent functionality with 99% fewer lines of code than OpenClaw.

📏 Real-time line count: run bash core_agent_lines.sh to verify anytime.

📢 News

2026-03-16 🚀 Released v0.1.4.post5 — a refinement-focused release with stronger reliability and channel support, and a more dependable day-to-day experience. Please see release notes for details.
2026-03-15 🧩 DingTalk rich media, smarter built-in skills, and cleaner model compatibility.
2026-03-14 💬 Channel plugins, Feishu replies, and steadier MCP, QQ, and media handling.
2026-03-13 🌐 Multi-provider web search, LangSmith, and broader reliability improvements.
2026-03-12 🚀 VolcEngine support, Telegram reply context, /restart, and sturdier memory.
2026-03-11 🔌 WeCom, Ollama, cleaner discovery, and safer tool behavior.
2026-03-10 🧠 Token-based memory, shared retries, and cleaner gateway and Telegram behavior.
2026-03-09 💬 Slack thread polish and better Feishu audio compatibility.
2026-03-08 🚀 Released…

View on GitHub

overview

🐈 nanobot is an ultra-lightweight personal AI assistant inspired by OpenClaw.

ironclaw

nearai / ironclaw

IronClaw is OpenClaw inspired implementation in Rust focused on privacy and security

IronClaw

Your secure personal AI assistant, always on your side

English | 简体中文 | Русский | 日本語

Philosophy • Features • Installation • Configuration • Security • Architecture

Philosophy

IronClaw is built on a simple principle: your AI assistant should work for you, not against you.

In a world where AI systems are increasingly opaque about data handling and aligned with corporate interests, IronClaw takes a different approach:

Your data stays yours - All information is stored locally, encrypted, and never leaves your control
Transparency by design - Open source, auditable, no hidden telemetry or data harvesting
Self-expanding capabilities - Build new tools on the fly without waiting for vendor updates
Defense in depth - Multiple security layers protect against prompt injection and data exfiltration

IronClaw is the AI assistant you can actually trust with your personal and professional life.

Features

Security First

WASM Sandbox - Untrusted tools run…

View on GitHub

overview

IronClaw is OpenClaw inspired implementation in Rust focused on privacy and security.

nullclaw

nullclaw / nullclaw

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

Official website: nullclaw.io

NullClaw

Null overhead. Null compromise. 100% Zig. 100% Agnostic.
678 KB binary. ~1 MB RAM. Boots in <2 ms. Runs on anything with a CPU.

The smallest fully autonomous AI assistant infrastructure — a static Zig binary that fits on any $5 board, boots in milliseconds, and requires nothing but libc.

Docs: English · 中文 · Contributing · Discord

678 KB binary · <2 ms startup · 5,300+ tests · 50+ providers · 19 channels · Pluggable everything

Features

Impossibly Small: 678 KB static binary — no runtime, no VM, no framework overhead.
Near-Zero Memory: ~1 MB peak RSS. Runs comfortably on the cheapest ARM SBCs and microcontrollers.
Instant Startup: <2 ms on Apple Silicon, <8 ms on a 0.8 GHz edge core.
True Portability: Single self-contained binary across ARM, x86, and RISC-V. Drop it anywhere, it just runs.
Feature-Complete: 50+ providers, 19 channels, 35+ tools, 10…

View on GitHub

overview

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig.

moltis

moltis-org / moltis

A Rust-native claw you can trust. One binary — sandboxed, secure, auditable. Voice, memory, MCP tools, and multi-channel access built-in.

Moltis — A Rust-native claw you can trust

One binary — sandboxed, secure, yours.

Installation • Comparison • Architecture • Security • Features • How It Works • Contributing

Moltis recently hit the front page of Hacker News. Please open an issue for any friction at all. I'm focused on making Moltis excellent.

Secure by design — Your keys never leave your machine. Every command runs in a sandboxed container, never on your host.

Your hardware — Runs on a Mac Mini, a Raspberry Pi, or any server you own. One Rust binary, no Node.js, no npm, no runtime.

Full-featured — Voice, memory, scheduling, Telegram, Discord, browser automation, MCP servers — all built-in. No plugin marketplace to get supply-chain attacked through.

Auditable — The agent loop + provider model fits in ~5K lines. The core (excluding the optional web UI) is ~196K lines across 46 modular crates you can…

View on GitHub

overview

A Rust-native personal AI assistant with voice, memory, sandboxing, MCP tools, and multi-channel access.

zclaw

tnm / zclaw

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

zclaw

The smallest possible AI personal assistant for ESP32.

zclaw is written in C and runs on ESP32 boards with a strict all-in firmware budget target of <= 888 KiB on the default build. It supports scheduled tasks, GPIO control, persistent memory, and custom tool composition through natural language.

The 888 KiB cap is all-in firmware size, not just app code It includes zclaw logic plus ESP-IDF/FreeRTOS runtime, Wi-Fi/networking, TLS/crypto, and cert bundle overhead.

Fun to use, fun to hack on

Full Documentation

Use the docs site for complete guides and reference.

Quick Start

One-line bootstrap (macOS/Linux):

bash <(curl -fsSL https://raw.githubusercontent.com/tnm/zclaw/main/scripts/bootstrap.sh)

Already cloned?

./install.sh

Non-interactive install:

./install.sh -y

Setup notes

bootstrap.sh clones/updates the repo and then runs ./install.sh. You can inspect/verify the bootstrap flow first (including ZCLAW_BOOTSTRAP_SHA256 integrity checks); see the Getting…

View on GitHub

overview

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

clawlet

mosaxiv / clawlet

Ultra-lightweight and efficient personal AI assistant

Clawlet

Ultra-lightweight and efficient personal AI assistant

Clawlet is a lightweight personal AI agent with hybrid semantic memory search — a single static binary with no runtime and no CGO.
Bundled SQLite + sqlite-vec. Drop it on any machine and memory search just works.

This project is inspired by OpenClaw and nanobot.

Install

Download from GitHub Releases.

macOS (Apple Silicon):

curl -L https://github.com/mosaxiv/clawlet/releases/latest/download/clawlet_Darwin_arm64.tar.gz | tar xz
mv clawlet ~/.local/bin/

Quick Start

# Initialize
clawlet onboard \
  --openrouter-api-key "sk-or-..." \
  --model "openrouter/anthropic/claude-sonnet-4.5"

# Check effective configuration
clawlet status

# Chat
clawlet agent -m "What is 2+2?"

Configuration (`~/.clawlet/config.json`)

Config file: ~/.clawlet/config.json

Supported providers

clawlet currently supports these LLM providers:

OpenAI (openai/<model>, API key: env.OPENAI_API_KEY)
OpenAI Codex (OAuth) (openai-codex/<model>, no API key; login: clawlet provider login openai-codex)
OpenRouter (openrouter/<provider>/<model>, API key: env.OPENROUTER_API_KEY)
…

View on GitHub

overview

Ultra-lightweight and efficient personal AI assistant.

rosclaw

PlaiPin / rosclaw

ROS2 meets OpenClaw 💗

RosClaw

Important

This project is undergoing a major re-architecture and migration to separate repos. Check back soon for updates, or reach out on X @irvinxyz to follow along.

Natural language control of ROS2 robots through messaging apps, powered by AI agents.

RosClaw connects OpenClaw to ROS2 (the Robot Operating System) through an intelligent plugin layer. Send a message on Telegram, WhatsApp, Discord, or Slack — the robot moves. Connect to your own robot or "lease" any robot registered into our portal globally. Each robot registers their own profile with capabilitie.

Whethere it's a cute desk robot or a humanoid robot, all you have to do is install our OpenClaw extension and run our ROS2 packakge.

Click to watch the demos

How It Works

User (WhatsApp/Telegram/Discord/Slack)
        |
        v
OpenClaw Gateway (AI Agent + Tools + Memory)
        |
        v  RosClaw Plugin
rosbridge_server (WebSocket)
        |
        v  ROS2 DDS
Robots: Nav2, MoveIt2, cameras, sensors

View on GitHub

overview

ROS2 meets OpenClaw.

geminiclaw

e-mon / geminiclaw

Personal autonomous agent powered by Gemini CLI. Orchestrates scheduling, persistent memory, MCP tools, and multi-channel messaging.

An extension for Gemini CLI that adds autonomous agent orchestration.
Scheduling · Memory · MCP Tools · Multi-channel Messaging

Why GeminiClaw?

GeminiClaw extends Gemini CLI — it doesn't replace it. All LLM reasoning, tool use, and sandbox execution happen inside Gemini CLI via ACP. GeminiClaw never touches OAuth tokens or calls backend services directly — it spawns Gemini CLI processes and communicates over stdio.

ACP process pool — Keeps warm Gemini CLI processes with session affinity. Stateful multi-turn conversations without replay overhead.
Thin orchestration layer — Scheduling is Inngest. Search is QMD. Messaging is Chat SDK. GeminiClaw is the glue, not another agent framework.
Sandboxed by default — Every agent run executes inside Gemini CLI's Docker sandbox. Tool use is isolated from day one.
Bring your own auth — Authentication is handled entirely by Gemini CLI. GeminiClaw supports whatever auth method you configure (Google OAuth, API key, Vertex AI).

…

View on GitHub

overview

Personal autonomous agent powered by Gemini CLI. Orchestrates scheduling, persistent memory, MCP tools, and multi-channel messaging.

ClawX

ValueCell-ai / ClawX

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https://clawx.com.cn.

ClawX

The Desktop Interface for OpenClaw AI Agents

Features • Why ClawX • Getting Started • Architecture • Development • Contributing

English | 简体中文 | 日本語

Overview

ClawX bridges the gap between powerful AI agents and everyday users. Built on top of OpenClaw, it transforms command-line AI orchestration into an accessible, beautiful desktop experience—no terminal required.

Whether you're automating workflows, managing AI-powered channels, or scheduling intelligent tasks, ClawX provides the interface you need to harness AI agents effectively.

ClawX comes pre-configured with best-practice model providers and natively supports Windows as well as multi-language settings. Of course, you can also fine-tune advanced configurations via Settings → Advanced → Developer Mode.

Screenshot

Why ClawX

Building AI agents shouldn't require mastering the command line. ClawX was designed with a simple philosophy: powerful technology deserves an interface that respects your time.

Challenge	ClawX Solution
Complex CLI setup	One-click installation with guided setup

…

View on GitHub

overview

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal.

claw-empire

GreenSheep01201 / claw-empire

Command Your AI Agent Empire from the CEO Desk — A local-first AI agent office simulator that orchestrates CLI, OAuth, and API-connected agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, and more) as a virtual autonomous company.

Claw-Empire

Command Your AI Agent Empire from the CEO Desk
A local-first AI agent office simulator that orchestrates CLI, OAuth, and API-connected providers (including Claude Code, Codex CLI, Gemini CLI, OpenCode, Kimi Code, GitHub Copilot, and Antigravity) as a virtual company of autonomous agents

Quick Start · AI Install Guide · Release Notes · OpenClaw · Direct Messenger · $ Command · Features · Screenshots · Tech Stack · Providers · Docker Deploy · Security

English | 한국어 | 日本語 | 中文

What is Claw-Empire?

Claw-Empire transforms your AI coding assistants — connected via CLI, OAuth, or direct API keys — into a fully simulated virtual software company. You are the CEO. Your AI agents are the employees. Watch them collaborate across departments, hold meetings, deliver tasks, and level up — all visualized through a charming pixel-art office…

View on GitHub

overview

Command Your AI Agent Empire from the CEO Desk — A local-first AI agent office simulator that orchestrates CLI, OAuth, and API-connected agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, and more) as a virtual autonomous company.

Ghostty - Use Fragment Shader as Terminal Background

0xkoji — Wed, 04 Mar 2026 06:06:55 +0000

What is Ghostty?

👻Ghostty is a GPU-based terminal emulator developed by Mitchell Hashimoto, co-founder of HashiCorp. It utilizes Metal on macOS and OpenGL on Linux for GPU rendering and takes advantage of this architecture to support custom shader functionality.

ghostty-org / ghostty

👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

Ghostty

Fast, native, feature-rich terminal emulator pushing modern features

A native GUI or embeddable library via libghostty

About
·
Download
·
Documentation
·
Contributing
·
Developing

About

Ghostty is a terminal emulator that differentiates itself by being fast, feature-rich, and native. While there are many excellent terminal emulators available, they all force you to choose between speed, features, or native UIs. Ghostty provides all three.

libghostty is a cross-platform, zero-dependency C and Zig library for building terminal emulators or utilizing terminal functionality (such as style parsing). Anyone can use libghostty to build a terminal emulator or embed a terminal into their own applications. See Ghostling for a minimal complete project example or the examples directory for smaller examples of using libghostty in C and Zig.

For more details, see About Ghostty.

Download

See the download page on the Ghostty website.

Documentation

See the documentation on the Ghostty website.

…

View on GitHub

How to run a Shader as the terminal background?

Step1 Create Ghostty config

mkdir ~/.config/ghostty
touch ~/.config/ghostty/config

Configuration

Ghostty supports hundreds of configuration options to make it look and behave exactly how you want.

ghostty.org

Step2 Create or download a Shader

mkdir shaders

noise.glsl

float random(in vec2 st) {
    return fract(sin(dot(st.xy, vec2(12.9898, 78.233))) * 43758.5453123);
}

vec2 random_gradient(in vec2 i) {
    float r = 2.0 * 3.1415926535 * random(i);
    return vec2(cos(r), sin(r));
}

float perlin_noise(in vec2 st) {
    vec2 i = floor(st);
    vec2 f = fract(st);

    vec2 g00 = random_gradient(i + vec2(0.0, 0.0));
    vec2 g10 = random_gradient(i + vec2(1.0, 0.0));
    vec2 g01 = random_gradient(i + vec2(0.0, 1.0));
    vec2 g11 = random_gradient(i + vec2(1.0, 1.0));

    vec2 p00 = f - vec2(0.0, 0.0);
    vec2 p10 = f - vec2(1.0, 0.0);
    vec2 p01 = f - vec2(0.0, 1.0);
    vec2 p11 = f - vec2(1.0, 1.0);

    float n00 = dot(g00, p00);
    float n10 = dot(g10, p10);
    float n01 = dot(g01, p01);
    float n11 = dot(g11, p11);

    vec2 u = f * f * (3.0 - 2.0 * f);

    float nx0 = mix(n00, n10, u.x);
    float nx1 = mix(n01, n11, u.x);
    float nxy = mix(nx0, nx1, u.y);

    return (nxy + 1.0) / 2.0;
}


void mainImage( out vec4 fragColor, in vec2 fragCoord )
{
    vec2 uv = fragCoord / iResolution.xy;
    vec2 noiseUV = uv * 4.0;
    noiseUV += iTime * 0.5;

    vec3 col = 0.5 + 0.5 * cos(iTime + noiseUV.xyx + vec3(0.0, 2.0, 4.0));
    float noise_val = perlin_noise(noiseUV);
    col *= noise_val;

    vec4 terminalColor = texture(iChannel0, uv);
    vec3 blendedColor = terminalColor.rgb + col.rgb * 0.7;

    fragColor = vec4(blendedColor,1.0);
}

custom-shader

Option Reference - Configuration

Reference of all Ghostty configuration options.

ghostty.org

If you don't have any Shader you want to use as the background, you can find out something cool in the following repo.

0xhckr / ghostty-shaders

A repository containing many free shaders to use with ghostty (the terminal)

Installation

Clone the repository:

git clone --depth 1 https://github.com/hackr-sh/ghostty-shaders
cd ghostty-shaders

Copy your preferred shader file to the Ghostty config directory:

cp <your-choice>.glsl ~/.config/ghostty/shaders/shader.glsl

Add the following line to your ~/.config/ghostty/config file to enable the custom shader:

custom-shader = ~/.config/ghostty/shaders/shader.glsl

View on GitHub

Step3 Add the Shader to the config

I downloaded water.glsl from the above repo. The nice thing is that Ghostty allows us to use multiple shaders.

custom-shader = ~/.config/ghostty/shaders/noise.glsl
custom-shader = ~/.config/ghostty/shaders/water.glsl
custom-shader-animation = true

After saving config, hit Cmd + Shift + , to apply the change to Ghostty.

Troubleshooting

If the background doesn’t change, check ‎custom-shader path exists and the Shader itself.

Happy hacking with Ghostty and shaders!

My Ghostty config

#==================================
# appearance
#==================================
# color theme
theme = Calamity
# shaders
#custom-shader = ~/.config/ghostty/shaders/gears-and-belts.glsl
custom-shader = ~/.config/ghostty/shaders/noise.glsl
custom-shader = ~/.config/ghostty/shaders/water.glsl
#custom-shader = ~/.config/ghostty/shaders/fern.glsl
#custom-shader = ~/.config/ghostty/shaders/cell.glsl
custom-shader-animation = true

#-----------------------------------
# Resize panes with arrow keys
#-----------------------------------
keybind = ctrl+shift+arrow_left=resize_split:left,10
keybind = ctrl+shift+arrow_right=resize_split:right,10
keybind = ctrl+shift+arrow_down=resize_split:down,10
keybind = ctrl+shift+arrow_up=resize_split:up,10

#-----------------------------------
# Split panes
#-----------------------------------
keybind = ctrl+shift+v=new_split:right
keybind = ctrl+shift+h=new_split:down

#-----------------------------------
# Move panes
#-----------------------------------
keybind = shift+arrow_left=goto_split:left
keybind = shift+arrow_right=goto_split:right
keybind = shift+arrow_up=goto_split:up
keybind = shift+arrow_down=goto_split:down


#-----------------------------------
# Control panes
#-----------------------------------
keybind = ctrl+x=close_surface

A Step-by-Step Guide: SSH into Your Parallels Ubuntu VM from a Mac

0xkoji — Thu, 26 Feb 2026 14:26:03 +0000

Running Ubuntu on Parallels Desktop is a fantastic way to develop on a Mac. However, working inside the virtual machine's window isn't always the most comfortable experience. Sometimes, you just want to stay in your native macOS Terminal, where all your familiar settings and shortcuts live.

Setting up SSH access from your Mac host to your Ubuntu guest OS is the perfect solution. Here is a quick, step-by-step guide on how to get it done.

1. Check Network Configuration

First, make sure that your guest OS network setting is configured correctly. Your virtual machine needs to use the Shared Network option.

If you haven't modified any advanced configurations in Parallels Desktop, your guest OS uses Shared Network by default, so you probably don't need to change anything here.

2. Setup OpenSSH Server (Ubuntu Side)

By default, Ubuntu desktop environments usually don't come with the SSH server installed and running. Open the terminal inside your Ubuntu virtual machine and run the following commands to set it up:

# update package list
sudo apt update

# install SSHserver
sudo apt install openssh-server -y

# start SSH service
sudo systemctl start ssh

# check ssh server service
sudo systemctl status ssh

If you see active (running) in green text, you are good to go!

3. Find Your IP Address and Username (Ubuntu Side)

o connect from your Mac, you need to know exactly where to connect and who you are connecting as.

Check the IP address:

hostname -I

You will see an IP address output. For Parallels Desktop using a Shared Network, it typically looks something like 10.211.55.xxx. Note this down.

Check your exact username:

whoami

Depending on how you set up the VM, you will probably see parallels, or perhaps your own name. Make sure to use the exact output from this command.

4. Connect via SSH from Mac

Now, switch back to your Mac and open your native Terminal app. Use the ssh command using the username and IP address you just confirmed:

# your_username: whoami
# your_ip_address: hostname -I
ssh <your_username>@<your_ip_address>

Things to keep in mind during your first connection:

You might see a message asking: Are you sure you want to continue connecting?. Type yes and press Enter.

When prompted for a password, use your Ubuntu user password, not your Mac login password or Parallels account password.

When typing your password, nothing will show up on the screen. This is normal security behavior—just type it and press Enter.

That’s it! You now have full terminal access to your Ubuntu VM directly from your Mac. Happy coding!

Troubleshooting Common Issues

Even with the right steps, you might run into a couple of common hiccups. Here is how to fix them.

1. Connection Timeout (No Response)

If you type the ssh command and nothing happens until it eventually times out, your Mac cannot reach the Ubuntu VM.

Double-check the IP Address: Did you make a typo? Parallels Shared Network IPs usually start with 10.211.55.. Make sure you didn't accidentally type 10.221... or another variation.
Check the Firewall (Ubuntu side): Sometimes, the Ubuntu firewall blocks SSH connections by default. Run this in your Ubuntu terminal to allow SSH traffic:

sudo ufw allow ssh
sudo ufw reload

Verify Network Settings: Go to your Parallels VM Configuration > Hardware > Network, and ensure the Source is set to Shared Network.

2. Password Authentication Fails (Permission Denied)

You connect successfully, but it keeps rejecting your password.

Use the right password: The terminal is asking for the Ubuntu virtual machine's login password (the one you use to unlock the Ubuntu desktop). Do not use your Mac host password or your Parallels Desktop account password.
Verify your username: Are you sure your username is parallels? Run whoami inside Ubuntu again to be 100% sure. If your username is john, your command must be ssh john@10.211.55.x.
Keyboard layout mismatch: Since passwords are hidden while typing, a different keyboard layout (like US vs. JIS) might cause you to type the wrong special characters. Try typing your password in a visible text editor on your Mac, copy it, and paste it into the terminal when prompted.

Clean up repo with knip and two-line prompt

0xkoji — Sat, 21 Feb 2026 23:45:35 +0000

This will work with AI code editor and AI CLI.

install kip

https://knip.dev/

webpro-nl / knip

✂️ Find unused files, dependencies and exports in your JavaScript and TypeScript projects. Knip it before you ship it!

Knip finds and fixes unused dependencies, exports and files in your JavaScript and TypeScript projects. Less code and dependencies lead to improved performance, less maintenance and easier refactorings.

Website: knip.dev
GitHub repo: webpro-nl/knip
Official npm packages: knip, @knip/create-config, @knip/language-server, @knip/mcp
Knip on the VS Code Marketplace, Knip on the Open VSX Registry
Contributing Guide
Follow @webpro.nl on Bluesky for updates
Sponsor Knip!

Contributors

Special thanks to the wonderful people who have contributed to Knip!

Knip

/'knɪp/ means "(to) cut" and is pronounced with a hard "K" 🇳🇱

License

Knip is free and open-source software licensed under the ISC License.

Parts of Knip have been inspired by and/or partially copy code from the following projects:

View on GitHub

bun add -D knip
pnpm add -D knip
npm install -D knip

send the prompt

prompt

Clean up the unused code using knip. Please also verify that the build, test and lint processes still pass as expected.

Prevent Hugging Face Spaces from Sleeping with GitHub Actions + agent-browser

0xkoji — Sun, 15 Feb 2026 21:18:05 +0000

Hugging Face Spaces are incredibly convenient for hosting demos, tools, and lightweight apps.

https://huggingface.co/

However, there is one limitation:

If a Space is not accessed for 48 hours, it goes to sleep.

This can be problematic when:
• You share a demo URL and it’s slow on first access (cold start)
• You host automation tools like n8n
• You want your app to always feel “ready”
• You want simple uptime monitoring

To solve this, I built a small automation:

GitHub Actions accesses my Space daily
agent-browser opens the page and takes a screenshot
The screenshot is posted to Discord

This achieves both:
• ✅ Preventing sleep
• ✅ Visual uptime monitoring

In this article, I’ll show you exactly how to set it up.

⸻

Why use agent-browser?

You could simply curl the Space URL.

But I wanted:
• A real browser access (not just HTTP ping)
• To confirm the page fully renders
• To capture a screenshot as proof
• To visually verify that nothing is broken

For that, I used agent-browser, a CLI browser automation tool built on Playwright.

It works perfectly inside GitHub Actions.

vercel-labs / agent-browser

Browser automation CLI for AI agents

agent-browser

Headless browser automation CLI for AI agents. Fast native Rust CLI.

Installation

Global Installation (recommended)

Installs the native Rust binary:

npm install -g agent-browser
agent-browser install  # Download Chrome from Chrome for Testing (first time only)

Project Installation (local dependency)

For projects that want to pin the version in package.json:

npm install agent-browser
agent-browser install

Then use via package.json scripts or by invoking agent-browser directly.

Homebrew (macOS)

brew install agent-browser
agent-browser install  # Download Chrome from Chrome for Testing (first time only)

Cargo (Rust)

cargo install agent-browser
agent-browser install  # Download Chrome from Chrome for Testing (first time only)

From Source

git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
pnpm build:native   # Requires Rust (https://rustup.rs)
pnpm link --global  # Makes agent-browser available globally
agent-browser install

Linux Dependencies

On Linux, install system dependencies:

agent-browser install --with-deps

Updating

Upgrade to the latest version:

agent-browser upgrade

Detects your installation method…

View on GitHub

⸻

The GitHub Actions Workflow

Here is the exact YAML file I use:

on:
  schedule:
    - cron: "0 0 * * *"

jobs:
  access-hugging-face-n8n:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v6

      - name: Install agent-browser
        run: npm install -g agent-browser

      - name: Install Playwright browsers
        run: agent-browser install --with-deps

      - name: Go to the hugging face space
        run: |
          agent-browser open ${{ secrets.HUGGING_FACE_SPACE_URL }}
          agent-browser wait --text "Sign in"
          agent-browser screenshot page.png
          agent-browser close

      - name: Notify Discord on done access
        if: success()
        run: |
          curl --fail-with-body -sS -X POST \
            -F 'payload_json={"content":"Hugging Face access job done."}' \
            -F "file1=@page.png;type=image/png" \
            "${{ secrets.DISCORD_WEBHOOK_URL }}"

⸻

How It Works

Scheduled Daily Run

cron: "0 0 * * *"

This runs once per day at 00:00 UTC.

⸻

Install agent-browser

npm install -g agent-browser
agent-browser install --with-deps

This installs Playwright and required browser dependencies inside the GitHub Actions runner.

⸻

Open the Hugging Face Space

agent-browser open ${{ secrets.HUGGING_FACE_SPACE_URL }}
agent-browser wait --text "Sign in"
agent-browser screenshot page.png
agent-browser close

What this does:
1. Opens the Space in a real browser
2. Waits until "Sign in" text appears (ensures full render)
3. Takes a screenshot
4. Closes the browser

The wait --text step prevents taking screenshots before the page is fully loaded.

You can change the text to something more specific to your app.

⸻

Post Screenshot to Discord

curl -X POST \
-F 'payload_json={"content":"Hugging Face access job done."}' \
-F "file1=@page.png;type=image/png" \
"${{ secrets.DISCORD_WEBHOOK_URL }}"

This sends:
• A success message
• The screenshot image

to your Discord channel via webhook.

Now you have both:
• Sleep prevention
• Daily visual health check

⸻

Setting Up Secrets

In your GitHub repository:

Settings → Secrets and variables → Actions

Add:
• HUGGING_FACE_SPACE_URL
• DISCORD_WEBHOOK_URL

These are securely injected into the workflow using:

${{ secrets.SECRET_NAME }}

⸻

Why This Approach Is Nice

✅ Free to run

GitHub Actions free tier is sufficient.

✅ No server required

No EC2, no cron server, no maintenance.

✅ Real browser check

Not just ping — full rendering validation.

✅ Visual confirmation

You instantly see if something broke.

✅ Easy to extend

Add monitoring, metrics, multi-Space support.

⸻

Optional Improvements

You could extend this further:
• Fail the job if specific text is missing
• Measure page load time
• Upload screenshots to S3 / R2
• Monitor multiple Spaces in parallel
• Add Slack notifications
• Store screenshots as GitHub Action artifacts

You can even turn this into a lightweight uptime monitoring system.

⸻

Conclusion

Hugging Face Spaces going to sleep can be inconvenient.

But with:

GitHub Actions + agent-browser

you can:
• Automatically keep your Space awake
• Capture daily screenshots
• Get notified via Discord
• Monitor visual health

All without running your own server.

Simple, effective, and fully automated.

One‑Line Magic: Using Claude Code Through Ollama

0xkoji — Sun, 01 Feb 2026 22:52:16 +0000

requirements

Ollama v0.15+
You have pulled a model via ollama pull

https://ollama.com/blog/launch

Run `ollama launch`

launch commands allow us to use a few AI coding agents.
Claude Code, Clawdbot(Openclaw), Codex, Droid, and OpenCode.

ollama launch
Select integration: 
  > claude - Claude Code (gpt-oss:20b)
    clawdbot - Clawdbot
    codex - Codex
    droid - Droid
    opencode - OpenCode

Then you will need to select a model you want use for Claude Code. (In this article, I used gpt-oss:20b model)

ollama launch

Launching Claude Code with gpt-oss:20b...

╭─── Claude Code v2.1.29 ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│                                                    │ Tips for getting started                                                                           │
│                 Welcome back baxin!                │ Run /init to create a CLAUDE.md file with instructions for Claude                                  │
│                                                    │ ─────────────────────────────────────────────────────────────────                                  │
│                                                    │ Recent activity                                                                                    │
│                       ▐▛███▜▌                      │ No recent activity                                                                                 │
│                      ▝▜█████▛▘                     │                                                                                                    │
│                        ▘▘ ▝▝                       │                                                                                                    │
│     gpt-oss:20b · API Usage Billing · baxin’s      │                                                                                                    │
│     Individual Org                                 │                                                                                                    │
│               ~\Desktop\dev\zenn-dev               │                                                                                                    │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯


 ‼Auth conflict: Both a token (ANTHROPIC_AUTH_TOKEN) and an API key (/login managed key) are set. This may lead to unexpected behavior.                    
    • Trying to use ANTHROPIC_AUTH_TOKEN? claude /logout                                                                                                   
    • Trying to use /login managed key? Unset the ANTHROPIC_AUTH_TOKEN environment variable.                                                               
  /model to try Opus 4.5                                                                                                                                   

───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
> Try "how does <filepath> work?"                                                                                                                          
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
  ? for shortcuts

OpenCode

0xkoji

Jan 13

How to Use Claude Opus 4.5 & Gemini 3 for Free with OpenCode

#ai #opencode #llm #programming

Comments 5

3 min read

How to Run Clawdbot Locally and Control It from Discord

0xkoji — Sun, 25 Jan 2026 06:39:31 +0000

Clawdbot

Clears your inbox, sends emails, manages your calendar, checks you in for flights.
All from WhatsApp, Telegram, or any chat app you already use.

https://clawd.bot/

Docs
https://docs.clawd.bot/start/getting-started

Supported platforms

WhatsApp
Telegram
Discord
Slack
Signal
iMessage
Claude
GPT
Spotify
Hue
Obsidian
Twitter
Browser
Gmail
GitHub

Install Clawdbot

requirements

Nodejs v22+
pnpm (recommended) Unfortunately, bun is not recommended

Step 1: Install Nodejs

# Download and install nvm:
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash

# in lieu of restarting the shell
\. "$HOME/.nvm/nvm.sh"

# Download and install Node.js:
nvm install 25

# Verify the Node.js version:
node -v # Should print "v25.4.0".

# Install Corepack:
npm install -g corepack

# Download and install pnpm:
corepack enable pnpm

# Verify pnpm version:
pnpm -v

https://nodejs.org/en/download/current

mise install nodejs 22.22.0

Step 2: Install Clawdbod

curl -fsSL https://clawd.bot/install.sh | bash

# version check
clawdbot -v
2026.1.23-1

Step 3: Generate a Discord bot token

Go to https://discord.com/developers/applications and create a new application. In this post, I name Clawdbot.
Go to Bot section in the sidebar and turn on the following
.
Then click Reset Token, and you can get a bot token. You will need to copy the token for onboarding.

Then go to OAuth2,

Step 4: Clawdbot onboarding

clawdbot onboard --install-daemon

🦞 Clawdbot 2026.1.23-1 (c8afa82)
   It's not "failing," it's "discovering new ways to configure the same thing wrong."

░████░█░░░░░█████░█░░░█░███░░████░░████░░▀█▀
█░░░░░█░░░░░█░░░█░█░█░█░█░░█░█░░░█░█░░░█░░█░
█░░░░░█░░░░░█████░█░█░█░█░░█░████░░█░░░█░░█░
█░░░░░█░░░░░█░░░█░█░█░█░█░░█░█░░█░░█░░░█░░█░
░████░█████░█░░░█░░█░█░░███░░████░░░███░░░█░
              🦞 FRESH DAILY 🦞
┌  Clawdbot onboarding
│
◇  Security ──────────────────────────────────────────────╮
│                                                         │
│  Please read: https://docs.clawd.bot/security           │
│                                                         │
│  Clawdbot agents can run commands, read/write files,    │
│  and act through any tools you enable. They can only    │
│  send messages on channels you configure (for example,  │
│  an account you log in on this machine, or a bot        │
│  account like Slack/Discord).                           │
│                                                         │
│  If you’re new to this, start with the sandbox and      │
│  least privilege. It helps limit what an agent can do   │
│  if it’s tricked or makes a mistake.                    │
│  Learn more: https://docs.clawd.bot/sandboxing          │
│                                                         │
├─────────────────────────────────────────────────────────╯
│
◇  I understand this is powerful and inherently risky.
Continue?
│  Yes
│
◇  Onboarding mode
│  QuickStart
│
◇  QuickStart ─────────────────────────╮
│                                      │
│  Gateway port: 18789                 │
│  Gateway bind: Loopback (127.0.0.1)  │
│  Gateway auth: Token (default)       │
│  Tailscale exposure: Off             │
│  Direct to chat channels.            │
│                                      │
├──────────────────────────────────────╯
│
◇  Model/auth provider
│  OpenAI
│
◇  OpenAI auth method
│  OpenAI Codex OAuth (Codex CLI)
│
◇  Model configured ──────────────────────────╮
│                                             │
│  Default model set to openai-codex/gpt-5.2  │
│                                             │
├─────────────────────────────────────────────╯
│
◇  Default model
│  Keep current (openai-codex/gpt-5.2)
│
◇  Channel status ────────────────────────────╮
│                                             │
│  Telegram: not configured                   │
│  WhatsApp: not configured                   │
│  Discord: not configured                    │
│  Slack: not configured                      │
│  Signal: not configured                     │
│  iMessage: not configured                   │
│  Nostr: install plugin to enable            │
│  Microsoft Teams: install plugin to enable  │
│  Mattermost: install plugin to enable       │
│  Nextcloud Talk: install plugin to enable   │
│  Matrix: install plugin to enable           │
│  BlueBubbles: install plugin to enable      │
│  Zalo: install plugin to enable             │
│  Zalo Personal: install plugin to enable    │
│  Tlon: install plugin to enable             │
│                                             │
├─────────────────────────────────────────────╯
│
◇  How channels work ─────────────────────────────────────╮
│                                                         │
│  DM security: default is pairing; unknown DMs get a     │
│  pairing code.                                          │
│  Approve with: clawdbot pairing approve <channel>       │
│  <code>                                                 │
│  Public DMs require dmPolicy="open" + allowFrom=["*"].  │
│  Multi-user DMs: set                                    │
│  session.dmScope="per-channel-peer" to isolate          │
│  sessions.                                              │
│  Docs:                                                  │
│  start/pairi                                            │
│  ng                                                     │
│                                                         │
│  Telegram: simplest way to get started — register a     │
│  bot with @BotFather and get going.                     │
│  WhatsApp: works with your own number; recommend a      │
│  separate phone + eSIM.                                 │
│  Discord: very well supported right now.                │
│  Slack: supported (Socket Mode).                        │
│  Signal: signal-cli linked device; more setup (David    │
│  Reagans: "Hop on Discord.").                           │
│  iMessage: this is still a work in progress.            │
│  Nostr: Decentralized protocol; encrypted DMs via       │
│  NIP-04.                                                │
│  Microsoft Teams: Bot Framework; enterprise support.    │
│  Mattermost: self-hosted Slack-style chat; install the  │
│  plugin to enable.                                      │
│  Nextcloud Talk: Self-hosted chat via Nextcloud Talk    │
│  webhook bots.                                          │
│  Matrix: open protocol; install the plugin to enable.   │
│  BlueBubbles: iMessage via the BlueBubbles mac app +    │
│  REST API.                                              │
│  Zalo: Vietnam-focused messaging platform with Bot      │
│  API.                                                   │
│  Zalo Personal: Zalo personal account via QR code       │
│  login.                                                 │
│  Tlon: decentralized messaging on Urbit; install the    │
│  plugin to enable.                                      │
│                                                         │
├─────────────────────────────────────────────────────────╯
│
◇  Select channel (QuickStart)
│  Discord (Bot API)
│
◇  Discord bot token ───────────────────────────────────╮
│                                                       │
│  1) Discord Developer Portal → Applications → New     │
│  Application                                          │
│  2) Bot → Add Bot → Reset Token → copy token          │
│  3) OAuth2 → URL Generator → scope 'bot' → invite to  │
│  your server                                          │
│  Tip: enable Message Content Intent if you need       │
│  message text. (Bot → Privileged Gateway Intents →    │
│  Message Content Intent)                              │
│  Docs:                                                │
│  discord                                              │
│                                                       │
├───────────────────────────────────────────────────────╯
03:41:11 [agents/auth-profiles] synced openai-codex credentials from codex cli
│
◇  Enter Discord bot token
│  <Discord bot token>
│
◇  Configure Discord channels access?
│  Yes
│
◇  Discord channels access
│  Open (allow all channels)
│
◇  Selected channels ──────────────────────────────╮
│                                                  │
│  Discord — very well supported right now. Docs:  │
│  discord                                        │
│  ]8;;                                           │
│                                                  │
├──────────────────────────────────────────────────╯
Updated ~/.clawdbot/clawdbot.json
Workspace OK: ~/clawd
Sessions OK: ~/.clawdbot/agents/main/sessions
│
◇  Skills status ────────────╮
│                            │
│  Eligible: 10              │
│  Missing requirements: 39  │
│  Blocked by allowlist: 0   │
│                            │
├────────────────────────────╯
│
◇  Configure skills now? (recommended)
│  Yes
│
◇  Preferred node manager for skill installs
│  npm
│
◇  Install missing skill dependencies
│  Skip for now
│
◇  Set GOOGLE_PLACES_API_KEY for goplaces?
│  No
│
◇  Set GOOGLE_PLACES_API_KEY for local-places?
│  No
│
◇  Set GEMINI_API_KEY for nano-banana-pro?
│  No
│
◇  Set OPENAI_API_KEY for openai-image-gen?
│  No
│
◇  Set OPENAI_API_KEY for openai-whisper-api?
│  No
│
◇  Set ELEVENLABS_API_KEY for sag?
│  No
│
◇  Hooks ──────────────────────────────────────────────╮
│                                                      │
│  Hooks let you automate actions when agent commands  │
│  are issued.                                         │
│  Example: Save session context to memory when you    │
│  issue /new.                                         │
│                                                      │
│  Learn more: https://docs.clawd.bot/hooks            │
│                                                      │
├──────────────────────────────────────────────────────╯
│
◇  Enable hooks?
│  Skip for now
│
◇  Gateway service runtime ──────────────────────────────╮
│                                                        │
│  QuickStart uses Node for the Gateway service (stable  │
│  + supported).                                         │
│                                                        │
├────────────────────────────────────────────────────────╯
│
◑  Installing Gateway service…
Installed LaunchAgent: /Users/koji/Library/LaunchAgents/com.clawdbot.gateway.plist
Logs: /Users/koji/.clawdbot/logs/gateway.log
◇  Gateway service installed
│
◇  
Health check failed: gateway closed (1006 abnormal closure (no close frame)): no close reason
  Gateway target: ws://127.0.0.1:18789
  Source: local loopback
  Config: /Users/koji/.clawdbot/clawdbot.json
  Bind: loopback
│
◇  Health check help ──────────────────────────────╮
│                                                  │
│  Docs:                                           │
│  https://docs.clawd.bot/gateway/health           │
│  https://docs.clawd.bot/gateway/troubleshooting  │
│                                                  │
├──────────────────────────────────────────────────╯
Missing Control UI assets. Build them with `pnpm ui:build` (auto-installs UI deps).
│
◇  Optional apps ────────────────────────╮
│                                        │
│  Add nodes for extra features:         │
│  - macOS app (system + notifications)  │
│  - iOS app (camera/canvas)             │
│  - Android app (camera/canvas)         │
│                                        │
├────────────────────────────────────────╯
│
◇  Control UI ────────────────────────────────────────────╮
│                                                         │
│  Web UI: http://127.0.0.1:18789/                        │
│  Web UI (with token):                                   │
│  http://127.0.0.1:18789/?token=2da11cb64b3563eeac74c45  │
│  f555882108610c614ce69d2db                              │
│  Gateway WS: ws://127.0.0.1:18789                       │
│  Gateway: not detected (gateway closed (1006 abnormal   │
│  closure (no close frame)): no close reason)            │
│  Docs: https://docs.clawd.bot/web/control-ui            │
│                                                         │
├─────────────────────────────────────────────────────────╯
│
◇  Workspace backup ──────────────────────────────────────╮
│                                                         │
│  Back up your agent workspace.                          │
│  Docs: https://docs.clawd.bot/concepts/agent-workspace  │
│                                                         │
├─────────────────────────────────────────────────────────╯
│
◇  Security ──────────────────────────────────────────╮
│                                                     │
│  Running agents on your computer is risky — harden  │
│  your setup: https://docs.clawd.bot/security        │
│                                                     │
├─────────────────────────────────────────────────────╯
│
◇  Dashboard ready ───────────────────────────────────────╮
│                                                         │
│  Dashboard link (with token):                           │
│  http://127.0.0.1:18789/?token=2da11cb64b3563eeac74c45  │
│  f555882108610c614ce69d2db                              │
│  Opened in your browser. Keep that tab to control       │
│  Clawdbot.                                              │
│                                                         │
├─────────────────────────────────────────────────────────╯
│
◇  Web search (optional) ─────────────────────────────────╮
│                                                         │
│  If you want your agent to be able to search the web,   │
│  you’ll need an API key.                                │
│                                                         │
│  Clawdbot uses Brave Search for the `web_search` tool.  │
│  Without a Brave Search API key, web search won’t       │
│  work.                                                  │
│                                                         │
│  Set it up interactively:                               │
│  - Run: clawdbot configure --section web                │
│  - Enable web_search and paste your Brave Search API    │
│    key                                                  │
│                                                         │
│  Alternative: set BRAVE_API_KEY in the Gateway          │
│  environment (no config changes).                       │
│  Docs: https://docs.clawd.bot/tools/web                 │
│                                                         │
├─────────────────────────────────────────────────────────╯
│
◇  What now ───────────────────────────────────────────╮
│                                                      │
│  What now: https://clawd.bot/showcase ("What People  │
│  Are Building").                                     │
│                                                      │
├──────────────────────────────────────────────────────╯
│
└  Onboarding complete. Dashboard opened with your token; keep that tab to control Clawdbot.

Step 5: Check Clawdbot gateway status

clawdbot gateway status

🦞 Clawdbot 2026.1.23-1 (c8afa82)
   If it works, it's automation; if it breaks, it's a "learning opportunity."

│
◇  
Service: LaunchAgent (loaded)
File logs: /tmp/clawdbot/clawdbot-2026-01-25.log
Command: /usr/local/bin/node /Users/koji/.npm-global/lib/node_modules/clawdbot/dist/entry.js gateway --port 18789
Service file: ~/Library/LaunchAgents/com.clawdbot.gateway.plist
Service env: CLAWDBOT_GATEWAY_PORT=18789

Config (cli): ~/.clawdbot/clawdbot.json
Config (service): ~/.clawdbot/clawdbot.json

Gateway: bind=loopback (127.0.0.1), port=18789 (service args)
Probe target: ws://127.0.0.1:18789
Dashboard: http://127.0.0.1:18789/
Probe note: Loopback-only gateway; only local clients can connect.

Runtime: running (pid 54025, state active)
RPC probe: ok

Listening: 127.0.0.1:18789
Troubles: run clawdbot status
Troubleshooting: https://docs.clawd.bot/troubleshooting

If everything works and you have access to http://127.0.0.1:18789/, you will see the following.

Step 6: Send a message to Clawdbot

Now, it's time to send a message to the bot on Discord.

Step 7: Use TUI (Terminal UI)

https://docs.clawd.bot/tui


clawdbot tui


 hello                                                         

 Hello.                                                        

 If you tell me one thing you want help with today, I’ll take  
 it from there.                                                
 Also: what should I call you?                                 
 connected | idle                                              
 agent main | session main (clawdbot-tui) |                    
 openai-codex/gpt-5.2 | tokens 9.4k/400k (2%)

Install Claude Code on Windows with scoop

0xkoji — Thu, 22 Jan 2026 04:01:41 +0000

install git via scoop

scoop install git

set path

setx CLAUDE_CODE_GIT_BASH_PATH "%USERPROFILE%\scoop\apps\git\current\usr\bin\bash.exe"

install `Claude Code`

irm https://claude.ai/install.ps1 | iex

https://code.claude.com/docs/en/setup#windows-powershell

Then restart Terminal app and run the following command.

claude --version
2.1.15 (Claude Code)

Use Cursor with Local LLM and LM Studio

0xkoji — Sun, 18 Jan 2026 02:07:56 +0000

Prerequisites

• Cursor installed
• LM Studio installed
• ngrok installed
• A local machine capable of running an LLM

For this guide, we’ll use the model: zai-org/glm-4.6v-flash

Step 1: Install LM Studio

Download and install LM Studio from the official website.
Once installed, launch the application.
https://lmstudio.ai/

Step 2: Download a Model

Inside LM Studio, download the model you want to use.
For this article, we use: zai-org/glm-4.6v-flash
Make sure the download completes successfully before moving on.

Step 3: Install ngrok

Install ngrok on your system.
ngrok allows you to expose your local server to the internet with a public URL.
https://ngrok.com/

If you have Homebrew, you can install ngrok easily

brew install ngrok

Step 4: Set Up ngrok

Complete the ngrok setup by following the instructions on the official ngrok Setup page.
This typically includes:
• Creating an ngrok account
• Authenticating your local installation with an auth token

ngrok config add-authtoken {your_token}

3 Step 5: Start the Local Server in LM Studio

1.Open LM Studio
2.Enable Developer Mode
3.Start the local server

LM Studio will now serve your local LLM using an OpenAI-compatible API.

Step 6: Expose the Local Server with ngrok

Open a terminal and run the following command:

ngrok http 1234

Note: 1234 should match the port used by LM Studio’s local server.
After running the command, ngrok will display a public URL like:
https://yours.ngrok-free.app
Copy this URL — you’ll need it for Cursor.

You'll see something like this

🚪 One gateway for every AI model. Available in early access *now*: https://ngrok.com/r/ai                                                                                                  

Session Status                online                                                                                                                                                        
Account                       your_account (Plan: Free)                                                                                                                         
Version                       3.35.0                                                                                                                                                        
Region                        United States (us)                                                                                                                                            
Latency                       19ms                                                                                                                                                          
Web Interface                 http://127.0.0.1:4040                                                                                                                                         
Forwarding                    https://something.ngrok-free.app -> http://localhost:1234                                                                                                  

Connections                   ttl     opn     rt1     rt5     p50     p90                                                                                                                   
                              7       0       0.00    0.00    6.26    263.91                                                                                                                

HTTP Requests                                                                                                                                                                               
-------------                                                                                                                                                                               

20:10:37.113 EST POST /v1/chat/completions      200 OK                                                                                                                                      
20:06:13.115 EST POST /v1/chat/completions      200 OK                                                                                                                                      
20:04:59.112 EST POST /v1/chat/completions      200 OK                                                                                                                                      
20:04:42.221 EST POST /v1/chat/completions      200 OK                                                                                                                                      
20:03:11.002 EST POST /v1/chat/completions      200 OK                                                                                                                                      
20:03:05.636 EST POST /v1/chat/completions      200 OK                                                                                                                                      
20:02:22.796 EST POST /v1/chat/completions      200 OK

Step 7: Open Cursor Settings

Launch Cursor and navigate to:

Settings → Models / OpenAI Configuration

Step 8: Configure the OpenAI Base URL

1.Enable OpenAI API Key
2.Enter any placeholder value for the API key
•In this example, we simply use: 1234
3.Paste the ngrok URL into Override OpenAI Base URL
4.Append /v1 to the end of the URL

Your final URL should look like this:

https://yours.ngrok-free.app/v1

Step 9: Add a Custom Model
1. Click Add Custom Model
2. Enter a name for your local LLM Example: GLM4.6-local

⚠️ Windows users:
You must enter the exact model name that LM Studio reports internally.
For this case, zai-org/glm-4.6v-flash

Done! 🎉

That’s it — the setup is complete.

You can now open Cursor Chat, enter a prompt, and send it. Cursor will route the request through ngrok to your local LLM running in LM Studio.

This setup allows you to enjoy Cursor’s powerful coding experience while keeping inference fully local.

Final Thoughts

Using Cursor with a local LLM is a great way to:
• Reduce API costs
• Improve privacy
• Experiment with custom or open-source models

LM Studio and ngrok make the process surprisingly straightforward. Once configured, it feels almost identical to using a hosted OpenAI model — except everything runs on your own machine.

Happy hacking! 🚀

https://buymeacoffee.com/koji

How to Use Claude Opus 4.5 & Gemini 3 for Free with OpenCode

0xkoji — Tue, 13 Jan 2026 07:14:05 +0000

🧵 TL;DR (Too Long; Didn’t Read)
Want to use powerful AI models like Claude Opus 4.5 and Gemini 3 for free? This guide walks you through setting up OpenCode with the Antigravity plugin and Google OAuth. You’ll be up and running with top-tier models in minutes—no paid API keys required.

🚀 Getting Started with OpenCode + Antigravity Auth

OpenCode is an open-source AI coding agent that lets you connect to models like Claude, GPT, Gemini, and more. It comes with free models out of the box, or you can bring your own from any provider.

In this guide, I’ll walk you through setting up OpenCode with Antigravity Auth using Google OAuth.

🛠 Step 1: Install OpenCode

You can install OpenCode using various package managers like Homebrew, npm, pnpm, yarn, scoop, choco, etc.

For this guide, I’ll use bun:

bun install -g opencode-ai

More install options: Installation Docs

⚙️ Step 2: Configure the Plugin

We’ll use opencode-antigravity-auth plugin. Follow the installation instructions in the repo. I’ll go with Option B here:

vim ~/.config/opencode/opencode.json

Add the plugin:

{
  "plugin": ["opencode-antigravity-auth@beta"]
}

🔐 Step 3: Authenticate with Google (Antigravity)

Make sure you have a Google account that supports Antigravity.

Run:

opencode auth login

You’ll see a provider list like this:

> Google
  OpenAI
  Anthropic
  GitHub Copilot
  ...

Select Google, then choose:

> OAuth with Google (Antigravity)

Your browser will open—sign in with your Google account. Once complete, you should see:

•  Multi-account setup complete (1 account(s)).
o  Login successful
—  Done

🧩 Step 4: Update Your Config

Now let’s update the full config file to include model definitions. Open:

vim ~/.config/opencode/opencode.json

And paste the full configuration block from the plugin’s documentation. (You can keep the version you shared above—no changes needed unless you want to customize models.)

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["opencode-antigravity-auth@latest"],
  "provider": {
    "google": {
      "models": {
        "antigravity-gemini-3-pro": {
          "name": "Gemini 3 Pro (Antigravity)",
          "limit": { "context": 1048576, "output": 65535 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
          "variants": {
            "low": { "thinkingLevel": "low" },
            "high": { "thinkingLevel": "high" }
          }
        },
        "antigravity-gemini-3-flash": {
          "name": "Gemini 3 Flash (Antigravity)",
          "limit": { "context": 1048576, "output": 65536 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
          "variants": {
            "minimal": { "thinkingLevel": "minimal" },
            "low": { "thinkingLevel": "low" },
            "medium": { "thinkingLevel": "medium" },
            "high": { "thinkingLevel": "high" }
          }
        },
        "antigravity-claude-sonnet-4-5": {
          "name": "Claude Sonnet 4.5 (Antigravity)",
          "limit": { "context": 200000, "output": 64000 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
        },
        "antigravity-claude-sonnet-4-5-thinking": {
          "name": "Claude Sonnet 4.5 Thinking (Antigravity)",
          "limit": { "context": 200000, "output": 64000 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
          "variants": {
            "low": { "thinkingConfig": { "thinkingBudget": 8192 } },
            "max": { "thinkingConfig": { "thinkingBudget": 32768 } }
          }
        },
        "antigravity-claude-opus-4-5-thinking": {
          "name": "Claude Opus 4.5 Thinking (Antigravity)",
          "limit": { "context": 200000, "output": 64000 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] },
          "variants": {
            "low": { "thinkingConfig": { "thinkingBudget": 8192 } },
            "max": { "thinkingConfig": { "thinkingBudget": 32768 } }
          }
        },
        "gemini-2.5-flash": {
          "name": "Gemini 2.5 Flash (Gemini CLI)",
          "limit": { "context": 1048576, "output": 65536 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
        },
        "gemini-2.5-pro": {
          "name": "Gemini 2.5 Pro (Gemini CLI)",
          "limit": { "context": 1048576, "output": 65536 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
        },
        "gemini-3-flash-preview": {
          "name": "Gemini 3 Flash Preview (Gemini CLI)",
          "limit": { "context": 1048576, "output": 65536 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
        },
        "gemini-3-pro-preview": {
          "name": "Gemini 3 Pro Preview (Gemini CLI)",
          "limit": { "context": 1048576, "output": 65535 },
          "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] }
        }
      }
    }
  }
}

🧠 Step 5: Select Claude Opus 4.5

Launch OpenCode:

opencode

Then press Ctrl + P and choose:

Switch model → Claude Opus 4.5 (Antigravity)

That’s it! You’re now ready to use OpenCode with Antigravity-authenticated models. Happy coding! 🌱

DEV Community: 0xkoji

Supply Chain Security measures

6 Must-know commands for cleaning up Homebrew packages

lucasgelfond / zerobrew

A 5-20x faster experimental Homebrew alternative

zerobrew

Install

Quick start

Performance snapshot

brew leaves

brew autoremove

brew doctor

brew cleanup

brew bundle dump

brew bundle --force cleanup

A Quick Look at Claw-Family

OpenClaw

openclaw / openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

🦞 OpenClaw — Personal AI Assistant

HiClaw

alibaba / hiclaw

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

Key Features

overview

NemoClaw

NVIDIA / NemoClaw

Run OpenClaw securely inside NVIDIA OpenShell with managed inference

NVIDIA NemoClaw: Reference Stack for Running OpenClaw in OpenShell

Quick Start

Prerequisites

overview

picoclaw

sipeed / picoclaw

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

PicoClaw: Ultra-Efficient AI Assistant in Go

$10 Hardware · <10MB RAM · <1s Boot · 皮皮虾，我们走！

overview

qwibitai / nanoclaw

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

🐳 Now Runs in Docker Sandboxes

Why I Built NanoClaw

overview

zeroclaw

zeroclaw-labs / zeroclaw

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

🦀 ZeroClaw — Personal AI Assistant

overview

nanobot

HKUDS / nanobot

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

nanobot: Ultra-Lightweight Personal AI Assistant

📢 News

overview

ironclaw

nearai / ironclaw

IronClaw is OpenClaw inspired implementation in Rust focused on privacy and security

IronClaw

Philosophy

Features

Security First

overview

nullclaw

nullclaw / nullclaw

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

NullClaw

Features

overview

moltis

moltis-org / moltis

A Rust-native claw you can trust. One binary — sandboxed, secure, auditable. Voice, memory, MCP tools, and multi-channel access built-in.

Moltis — A Rust-native claw you can trust

overview

zclaw

tnm / zclaw

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

zclaw

Full Documentation

Quick Start

overview

`brew leaves`

`brew autoremove`

`brew doctor`

`brew cleanup`

`brew bundle dump`

`brew bundle --force cleanup`

Configuration (`~/.clawlet/config.json`)