Stop using your laptop / Mac mini / VPS... Introducing cloud computers for AI agents: - 4 vCPU, 8 GB RAM spun up in <1s - Built-in computer use - Snapshots for easy cloning - Persistent files, packages, config - Public URLs for local ports We're launching today through an invite-only beta program. Early access includes 20 vCPU, 40GB RAM for free. If you want to try, comment or DM me.show more

introducing Space: a cloud filesystem built for work instead... of waiting, you can: → mount one persistent drive for you and your agents → instantly work in the cloud like local → only stream the bytes you need → no compression on any of your files try it for yourself todayshow more

today I went from $305/mo on Google Cloud to... $14/mo on Hetzner today I upgraded from 1 vCPU, 2GB RAM & no storage to 4 vCPU, 8GB RAM, 160GB SSD I can spin up 20 of such VMs and deploy my infra in multiple regions and still be cheaper on Hetzner vs Google Cloud this is, in fact, the real Cloud that was promised to usshow more

Today we're launching Sailboxes: the first cloud environment purpose-built... for long-horizon AI agents. Sailboxes are full machines with persistent state that auto-sleep, built for agents that live forever, priced so you only pay for what they actually use. From $0.015 per active vCPU-hour, over 70% cheaper than other providers. Under the hood: novel architecture from Nirvik Baruah and that live-migrates VMs based on actual resource usage. To show how robust it is, we ran a Minecraft server in a Sailbox and forced it to migrate every 2 minutes--players never noticed.show more

AI can now hold your product 👇 This is... a revolution for D2C brands... we're launching tomorrow, comment if you want early accessshow more

𝗛𝗲𝗿𝗺𝗲𝘀 Agent needs 8 GB RAM minimum to run... on local model. 🤯 The catch: the 3B and 9B models in the Ollama guide's table can't call tools. 𝗛𝗲𝗿𝗺𝗲𝘀 can chat, but not act. The official 𝗛𝗲𝗿𝗺𝗲𝘀 Agent 0.22.5 docs give real numbers, and 𝗛𝗲𝗿𝗺𝗲𝘀 checks your machine for you: ▸ 8 GB RAM: the minimum, for 3B models (chat only) ▸ 8–16 GB Mac: Qwen3.5-9B, the Mac guide's "sweet spot" ▸ 24+ GB RAM: gemma4:31b, the Ollama guide's pick for tool use ▸ 32+ GB RAM: the recommended setup for 27B+ models ▸ GPU: 8 GB+ runs small models, 16 GB+ runs 27–35B at high quality Whatever you pick, 𝗛𝗲𝗿𝗺𝗲𝘀 needs a 64K context. The guide says Ollama defaults to 2,048 tokens. On Ollama: set num_ctx 64000, then hermes setup → Custom Endpoint. Start with: Settings → Providers → Local Models in the Desktop app (terminal: hermes model). Each model shows green, amber or red for your machine before you download. How much RAM is in the machine you'd run 𝗛𝗲𝗿𝗺𝗲𝘀 on?show more

Want to code using GPT-4? We made an IDE... built for programming alongside it Try out the public beta here:show more

holy sh*t, Oracle literally gives you a 4 OCPU,... 12GB RAM VPS + 200GB storage for $0😳 meet Oracle Cloud Free VPS -4 OCPU threads & 12GB RAM -200GB block storage & 10TB monthly bandwidth -$300 in extra credits for 30 days (in eligible countries) -no domain needed (real card + ID required) -completely FREE (capacity depends on your region) claim it here: bookmark this quickshow more

21st Agents is now in Public Beta. The infra... layer to ship Claude Code &amp; Codex agents inside your product. In minutes. Comment for free credits to try 🧵show more

What if your cloud agents could use iOS and... Android devices just like that? Introducing Agent Device Cloud: hosted on your dusted Mac Mini, used through 𝚊𝚐𝚎𝚗𝚝-𝚍𝚎𝚟𝚒𝚌𝚎show more

Today we're launching local scheduled tasks in Claude Code... desktop. Create a schedule for tasks that you want to run regularly. They'll run as long as your computer is awake.show more

We spun up 100 Android VMs on InstaBox and... recorded their desktops. 400 vCPU, 800GB memory in total. All 100 VMs ready in under 10s, with only about $0.01 in compute used. Try out today ☁️show more

Today we're launching OpenCode on Clawi. Code in your... browser in a secure cloud environment—without ever giving an agent access to your personal computer. To celebrate, we’re increasing all agent limits at no extra cost: Basic + Pro: 2 agents, Ultra: 6 parallel agents.show more

Introducing BlitzClean ! A free, open-source RAM monitor +... disk cleaner for Mac I built it based on 3 things: - I kept running out of storage - I never knew what was eating my RAM - Memory Clean 2 stopped working for me on the macOS 27 beta (Golden Gate) What it does: - CPU, RAM and free disk in the menu bar - Ranks apps + AI agents (Claude Code, Codex, Cursor) by RAM, so you can pause or quit the ones you forgot about - Finds what fills your disk - Cleans caches, node_modules, simulators, Docker and old worktrees (you review everything first) MIT, runs 100% locally Made the video with Opus 5.5 medium, what do you think ?show more

Introducing agent-desktop agent-browser, for your whole computer → Computer... Use for any coding agent → macOS, Windows and Linux → Runs in bg while you keep working → Agents use your computer in parallel, each with its own cursorshow more

You can now create read-only database users for Laravel... MySQL databases in Laravel Cloud. Great for granting access to agents or even for humans tbh.show more

today, we're launching Resend Inboxes. an inbox for people... and their agents. ∙ connect the agents you already use through MCP or skills ∙ agents and humans reply from the same thread get started with Inboxes now:show more

my cursed photo editing app is ready for beta... testers send me a dm if you want to try it *** details: - seam carving algorithm for content-aware scaling - computer vision models (apple vision and roboflow RF-DETR) used to detect people - objects - key areas of an image - everything runs locally on your iphone *** let me know if you want a test invite :]show more

Railway has a free cloud VM with Claude Code,... Codex, Cursor CLI and other coding agents preinstalled. It's super easy to use. Just run one SSH command: ssh Each VM comes with 2 vCPU and 2GB RAM. You get 60 minutes to build, then 24 hours to claim it before the VM and its files are deleted. I tried it and recorded the setup, plus tests with several coding agents. You'll need GitHub login and an active Railway trial to claim the VM.show more

Introducing local realtime voice transcription. Speak freely to your... agents, without sending your voice data to the cloud. Available for Mac, Windows - and now also Linux!show more