@lgrammel
Account based inGermany!
About this account
- Account based in
- Germany
- Connected via
- Germany App Store
X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
Working on software factories.
Joined May 2009
- Tweets5.5K
- Following375
- Followers8.2K
- Likes13.8K
Pinned Tweet
25-min talk on the AI SDK factory I built
- why I built it
- how it works
- the impact so far
- what I’ve learned about software factories
youtube.com/watch?v=wnydmnIY…
Lars Grammel retweeted
I can’t stress enough how little an idea matters compared to the agency of the people executing the idea.
I have had the privilege of knowing and sometimes even working with some of the most successful people (by various metrics).
The difference between mediocre and excellent work and outcomes is predominantly one of agency.
In practice this means: they dont wait for things to happen to them they go out and make things happen for them.
They don’t wait for someone else to do something, for someone to teach them, for someone to give them the path, etc. They just go out and find a way to do it.
I think the single biggest superpower these people have is the realization/belief that the world around them is completely mutable. Most everything that happens is because a person made it happen.
I used to tell people to look around the room you’re sitting in. Look at everything. Every noun. It almost all exists because a person willed it into existence. Nothing is stopping you from doing the same.
I see people online all the time dismissing someone else’s success because “I had that idea first” or whatever. I mean… yeah? If so then the difference is… you. So a bit of a self own whenever I hear that.
Number one tip: act with agency.
Lars Grammel retweeted
Which term resonates most with you for project-level AI automations, including but not limited to coding agents?
72%Software Factory
12%Software Studio
10%Software Workbench
5%Software Workshop
80 votes • Final results
Vercel Connect is now GA.
You can use @𝚟𝚎𝚛𝚌𝚎𝚕/𝚌𝚘𝚗𝚗𝚎𝚌𝚝/𝚊𝚒-𝚜𝚍𝚔 to securely connect your AI SDK agents to MCP servers.
![Code snippet showcasing the import of libraries and functions for connecting to an MCP client and using an AI SDK with OAuth authentication:
import { createMCPClient } from '@ai-sdk/mcp';
import { connectAuthProvider } from '@vercel/connect/ai-sdk';
import { streamText } from 'ai';
const mcpClient = await createMCPClient({
transport: {
type: 'http',
url: 'https://mcp.linear.app',
authProvider: connectAuthProvider('oauth/linear', {
subject: { type: 'user', id: userId },
scopes: ['read'],
}),
},
});
const result = await streamText({
model: 'openai/gpt-5.6-sol',
tools: await mcpClient.tools(),
prompt,
});](/pic/https%3A%2F%2Fpbs%2Etwimg%2Ecom%2Fmedia%2FHQlV%2Dx7aIAAUIG0%2Ejpg%3Fname%3Dsmall%26format%3Dwebp)
ALT Code snippet showcasing the import of libraries and functions for connecting to an MCP client and using an AI SDK with OAuth authentication: import { createMCPClient } from '@ai-sdk/mcp'; import { connectAuthProvider } from '@vercel/connect/ai-sdk'; import { streamText } from 'ai'; const mcpClient = await createMCPClient({ transport: { type: 'http', url: 'https://mcp.linear.app', authProvider: connectAuthProvider('oauth/linear', { subject: { type: 'user', id: userId }, scopes: ['read'], }), }, }); const result = await streamText({ model: 'openai/gpt-5.6-sol', tools: await mcpClient.tools(), prompt, });
Vercel Connect is now generally available.
Give your apps and agents secure access to @slackhq, @linear, @github & 100+ other services.
• Short-lived, scoped access tokens
• Token and trigger observability
• RBAC and audit trails
vercel.com/blog/the-end-of-c…
Lars Grammel retweeted
We're introducing Run SDK: secure 𝚎𝚟𝚊𝚕 for dynamic Code Mode execution.
When agents write code, you don't always need a full sandbox. You can 𝚛𝚞𝚗 their code in a lightweight QuickJS secure context. Faster and more cost-efficient.
𝚗𝚙𝚖 𝚒 𝚛𝚞𝚗
vercel.com/blog/introducing-…
Lars Grammel retweeted
Vercel's AI SDK 7 ships HarnessAgent, an API for running established agent harnesses like Claude Code, Codex, and Pi. Write the agent once, then use whatever harness is best for your use case.
Try building a creative production agent with @pidotdev using the @vercel AI SDK: one image model makes the hero shot, then an E2B sandbox runs Python to cut the backdrop, render every specified size, overlay copy, audit WCAG contrast and palette share, and serve the finished ad set on a live URL.
Full example in the cookbook: github.com/e2b-dev/e2b-cookb…
Which term resonates most with you for project-level AI automations, including but not limited to coding agents?
72%Software Factory
12%Software Studio
10%Software Workbench
5%Software Workshop
80 votes • Final resultsMany software factory developers seem to assume that the factory they developed for their own project is the holy grail and that every project should use their particular workflows, agents, and prompts.
Lars Grammel retweeted
25-min talk on the AI SDK factory I built
- why I built it
- how it works
- the impact so far
- what I’ve learned about software factories
youtube.com/watch?v=wnydmnIY…
Lars Grammel retweeted
Introducing is-agentic.com, a tool to measure how well agents can read your site. Backed by @oradotai's research, you can run:
▪︎ Audits with 100+ checks
▪︎ Visualizations of agents using your site
▪︎ One-click prompts to fix problems
▪︎ A CLI for agents
Lars Grammel retweeted
A must watch for open source maintainers with a huge backlog of issues.
25-min talk on the AI SDK factory I built
- why I built it
- how it works
- the impact so far
- what I’ve learned about software factories
youtube.com/watch?v=wnydmnIY…
Related blog post: vercel.com/blog/building-a-s…
I'm about halfway through Matt's course now and find it super useful for understanding and thinking about coding agents.
Do you feel in control when you're coding with AI?
Can you:
- Get it to build the thing you wanted?
- Stop it making the same mistakes every time?
- Schedule huge chunks of work?
Or are you hanging on by your fingernails?
My new course is $199 this week. It's for you.
Lars Grammel retweeted
I've become extremely cloud agent-pilled. I still haven’t setup my laptop for local development since joining Cognition and it’s still unclear to me when I will have to. Working with Devin in Slack (with coworkers) and the webapp with the latest crop of models is better in every possible way so far, even for frontend work
Lars Grammel retweeted
Introducing fx, a tiny, open, native coding agent from Vercel Labs.
Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it.
fx is built on three principles:
1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?"
2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes.
3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP.
Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms.
You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: fx.sh/try).
Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic.
fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X (fx.sh/xchat) or file issues (fx.sh/issues).
𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑
fx.sh/
Lars Grammel retweeted
Do you feel in control when you're coding with AI?
Can you:
- Get it to build the thing you wanted?
- Stop it making the same mistakes every time?
- Schedule huge chunks of work?
Or are you hanging on by your fingernails?
My new course is $199 this week. It's for you.