Surprising how "unix-y" Omarchy feels in the sense of small separate tools. I screenrecorded with one tool, clipped with another, added captions with a third. And it all happened faster than using an all-in-one suite, with more control at each step. So interesting.

A physical 9-track magnetic tape from 1991 containing a copy of WordPerfect for Unix. Software was distributed on 1600 bpi tapes long before internet downloads became the standard.

🚀 Codex CLI 0.125.0 is out! 🔌 App-server Unix socket transport and resume/fork pagination 🔐 Permission profiles round-trip across TUI, MCP, and app-server 📦 Remote plugin install and marketplace upgrades Changelog:

After the Meta keynote, gotta say ... it does look like the computer industry is K-shaping toward: • Unix workstations (like Omarchy) • Non-computer devices (glasses, phones, tamagotchis...) First time Apple looks behind on multiple fronts.

Track money and time in plain text files you fully control. - Double-entry accounting, any currency - Fast: 25k transactions per second - Works on Mac, Windows, Unix Explore it here:

Our philosophy on extending 𝚏𝚡: open protocols. ∙ MCP (modelcontextprotocol⁠.io) ∙ Skills (agentskills⁠.io) ∙ Plugins (agent-plugins⁠.org) And the best one, Unix: ① Small programs that do one thing well and compose by calling other programs. ② 𝚕𝚒𝚋𝚏𝚡 that enables embeddability into more complex programs. You should be able to build your own CLI, background agent, software factory. Local or cloud.

# Practical ways to use the Claude Agent SDK 🛡 Build defense in depth with prompt injection countermeasures, credential proxies, and least privilege. Secure Deployment provides isolation techniques, credential proxy patterns, and network/filesystem controls for safe production agent operation. 📌 Title: Deploying AI Agents Securely 🔗 URL: 🧩 Overview Combines sandbox-runtime / Docker / gVisor / Firecracker isolation, credential proxy patterns, and network/filesystem controls for multi-layered defense. 🛠 How to use it Choose isolation by threat level: sandbox-runtime for single developer/CI, gVisor/Firecracker for multi-tenant or untrusted content. Inject credentials via Envoy / mitmproxy / LiteLLM proxies outside the agent boundary. 🏗 Practical usage - Credential proxy pattern: inject API keys at a proxy outside the agent boundary. The agent calls APIs without ever seeing credentials. Route via `ANTHROPIC_BASE_URL`. - Least privilege: mount only required directories as read-only, exclude `.env` / `~/.aws/credentials` / `*.pem`, use `--network none` + Unix socket proxy. - In cloud environments, use private subnets + cloud firewalls to block all outbound except through the proxy, which enforces allow-lists, injects credentials, and logs all traffic. 💡 Use cases 🔐 Credential management outside agent boundaries 🌐 Network restrictions preventing unauthorized data exfiltration 🏢 Strong isolation for multi-tenant environments ⚠️ Watch out Untrusted content (READMEs, web pages, user input) may contain prompt injection attempts. Network controls are your last line of defense — always configure them. #ClaudeAgentSDK# #AI#

We spent an evening in NYC with @BlockRunAI @dynamic_xyz, and @FireblocksHQ exploring what agents need to transact. Circle Agent Stack gives builders the infrastructure to create agent wallets, set policies, discover services, call APIs, and pay in USDC. Strong demos, sharp questions, and a room full of developers building toward the agentic economy. Give your agent the tools to transact:

Good moment today to remind everyone to stay frosty with AI. I was working on making a server stoppable via the CLI, and Codex decided the best path forward was to implement an unauthenticated network API to every server to shut itself down. Excellent work. I responded with "I don't know about that." (I usually give more direct feedback but this was so absurd) and it thought for like 20 seconds and responded "Server stopping should not be part of an unauthenticated network API." Yes. lol. By the way, the result I was looking for was that we automatically start a locally discovery Unix-socket bound server so I wanted it to discover that (using prior mechanisms already made) and gracefully stop that. The driver is absolutely accountable here (me). My lazy prompting led AI to think I wanted to be able to stop ANY configured server I was talking to. Shame on me for thinking it was obvious here. But, I also reviewed it and found this idiocy, so, that's where good AI drivers come in. Also me.