agent-os: Fast AI
From the repo · “A portable open-source operating system for agents. ~6 ms coldstarts, 32x cheaper than sandboxes. Powered by WebAssembly and V8 isolates.”
Create portable AI agents using fast and cost-effective technology.
"A founder wants to automate a customer welcome process. They set up an agent-os instance, connect it to their Notion database and Resend email service, and use 3 simple steps: 1) When a new customer signs up, the agent adds them to Notion. 2) The agent checks for any existing conversations with that customer and adds a new note to the conversation in Notion. 3) The agent sends a welcome email to the customer using Resend. The result is a seamless customer welcome system that frees up the founder's time for other tasks."
- •When you need to deploy AI models at the edge with minimal latency
- •When you want to reduce the cost of running AI workloads in the cloud
- •When you require a high degree of isolation and security for your AI agents
node src/cli.js deploy --agent src/example/agent.ts --wasm src/example/agent.wasm
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/agent-os && curl -fsSL https://workflowstacks.com/api/skills/agent-os/claude-skill -o ~/.claude/skills/agent-os/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Agent-os: Fast AI is a very large Rust project (~429k lines across 1464 code files, plus 719 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.
- 1README.mdStart here — what it does and how to install it
- 2AGENTS.mdThe instructions the AI actually follows
- 3Cargo.tomlDependencies and the commands it exposes
- 4examples/agent-to-agent/README.mdA worked example — copy this to get going
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/agent-os && curl -fsSL https://workflowstacks.com/api/skills/agent-os/claude-skill -o ~/.claude/skills/agent-os/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/agent-os?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Do this with a working workflow
Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.
Abandoned Cart Win-Back
Draft a personalized, non-pushy win-back email for every abandoned cart — referencing the exact product left behind. You approve before sending.
Outcome guideRecover abandoned carts with personalized emails
Export abandoned carts to a Google Sheet and the workflow drafts a warm, specific win-back email for each — referencing the actual product, without desperate discount-spam. You review and send.
Related skills
More ai-agent tools founders pair with this one.