I’ve spent the past four months building fx. We’re open sourcing it today.
I cared most about making it fast, small, and easy to embed:
10µs cold start
6.3 MiB native binary
single-digit megabytes of memory at baseline
structured output, ACP, and WebAssembly
Getting fx to this point has been a great experience, especially working closely with @EstebanSuarez and @rauchg and being mentored directly by both of them.
Try it and give us feedback. Join the X group chat for updates and a closer look at how we’re approaching fx and where it’s headed:
https://t.co/ihUJsRoj0Q
https://t.co/6TAVw5vgNl
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: https://t.co/wf2Trg47sC).
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 (https://t.co/A2AB2YythC) or file issues (https://t.co/GEjTHSoa1J).
𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑
https://t.co/g2uEuXhGnt
@mjlbach@vercel_dev This is exactly the kind of thing I hoped people would build with fx. Remote sessions over Tailscale RPC feel like a natural fit. Excited to see where you take it.
fx v0.0.5:
▫️ 4.2% smaller (6.13mb)
▫️ Grok and Codex subscription support
▫️ Project-local skills
▫️ Improved security
▫️ Many bugfixes & QoL improvements
fx upgrade ⋅ curl -fsSL https://t.co/qR3nSdKCaP | bash
https://t.co/AFaqPCQkPK
I used 𝚏𝚡 to build Mini, a personal web browser.
Many times I need to screen share, stream, or just test something without the 'bloat' and state of my browser. So I go Mini.
This was a cool test for https://t.co/OL0LzGtvAw and open models. It was the first time I experienced how cheap, but also how *good* these things can be.
'Personal software' is a hot topic. "I spent $25,000USD to cancel my $10 XYZ subscription" is a real thing 😂 (especially in Enterprises these days).
But I think open and local models will change this dynamic very profoundly. Software will really become spontaneous.
ps: shoutout to Orion browser who inspired me with 'focus mode'. I wanted my browser to be even more minimal, hackable, and run on Chromium.
vercel's coding agent fx, running inside a cloudflare worker 🤯
fx is wasm and needs jspi node hides it behind a flag, workerd just ships it on.
no child process. 36ms to a live tui streamed over a websocket.
https://t.co/J4gzlPaap9
I wanted to try Ox Alpha in https://t.co/o6xROMMGow
I have been using https://t.co/o6xROMMGow from the day it was launched and I think it’s a great competitor to pi agent.
Really loved how fast it is and low less memory it consumes @fazxes
So I took some time and build /setup to run any OpenAI compatible endpoint with https://t.co/o6xROMMGow
Now I have connected fx with openrouter api key and started using Ox Alpha.
Not sure of performance yet excited to test it out today
using @vercel's new coding agent https://t.co/QAdNUa3CRM from my phone using @shellular_dev!!
it's running on my hetzner vps.
i just installed and set it up in like 2 minutes while sitting in the bus :)
cc @rauchg@fazxes 👀