fx :Tiny, open, native coding agent.

For all the people asking "Why?", it seems like TFA has a pretty good list of features/attributes that it thinks sets it apart:

- fx is a coding agent harness and CLI written in Zig, optimized for research and embeddability as part of larger systems.

- It focuses on minimalism and performance across the board, from system prompt design, to its tools, feature set, and 6.39mib binary.

- For end users, its CLI output style and form factor aims to be closer to a Unix shell than a heavy "IDE in the terminal" TUI.

- It's open source (Apache-2.0), model-agnostic, and suitable for both local and cloud inference.

- Designed for instant installation and embedding in resource constrained environments and agent sandboxes.

- fx cold starts in 10µs and does no unnecessary work or I/O prior to accepting user input, making it ideal for programmatic use.

- Optimal fx.wasm builds produced by the Zig toolchain, which further reduce fx's size, making the network stack pluggable.

- fx contributes single-digit megabytes of memory baseline, allowing you to pack many instances in one machine.

- fx preserves scroll history by default, produces minimal output, and makes sparing use of complex TUI or paints

- Minimal system prompt and tools, to save on token costs and to yield optimal time-to-first-token performance (TTFT).

- Small core, extended via skills, plugins, MCPs, with a Unix-like philosophy to extensibility.

- Designed to work with local models, gateways, direct provider API access or subscriptions.

It may come across harsh but IMHO the only interesting thing about this project is that it is written in Zig. That's it.

Everything else in the harness is largely the same just Vercel-flavoured.

The portability benefit is also a bit over-sold imho. I wrote a harness in Go and it is as portable as this ... in fact it deploys straight into Vercel's own sandbox environment on demand without any issues.

That being said, did you say GLM 5.2 free? I need to look into that. GLM is remarkably capable model and that alone is worth using the harness in my books.

It does looks really interesting and definitely something I'll check out, but (genuine question), should "agent" and "agent harness" be used interchangeably as it is on here? It describes itself as an agent harness, but the tagline is "tiny, open, native coding agent".

I'm not sure harness is the right word either, but that seems to be what the industry has settled on so I'll concede on that, but surely the agent is the thing doing the work (which I guess is the model, or an instance of the model which is why agent is different?), whereas the harness is how the user interacts with the agent. We've had ways to describe that relationship before; client and server, frontend and backend, but again, I'll concede that the shiny new thing doesn't want to use boring old terminology, but I think some consistency and logic in the shiny new terminology is pretty important

That isn't specifically about fx of course, more of a general industry complaint

>Tiny ~6mb binary

I wonder why it's so large for a program written in Zig. It's basically just a loop that accepts user input, prepares the context, sends it to the LLM, parses the output, invokes the tools, and presents it all in the terminal. Add the built-in prompts and a few checks here and there (like blocking a write tool call before the file has been read first), and I'd expect a truly tiny native agent to be around 200-300 KB max.

They should spend their efforts making a harness that utilizes tiny AI models on the host in unison with the frontier model, to improve intelligence and capabilities. This is an under-explored area.

Just tried and although it’s not that polished or fast imo it’s very cool.

GLM 5.2 totally free even with a free Vercel account.

Make business sense too - fx is the entry point to bring more user to Vercel AI.

I'm not in the tech industry. Could someone explain why there are so many new coding agents, and why they're commonly upvoted on HackerNews? It seems like there's a new one in the top 10 every other day.

I like it from trying it quickly, but is there any way to use it with a provider other than vercel?

Local inference? I see no other way than to sign up for a vercel account, so pass.

I wonder how long will the "curl my arbitrary script and pipe it to bash" will continue being a delivery method.

I couldn’t find an option to connect to a generic OpenAI-compatible endpoint - did I miss it?

Will dive in later to see how its contribution/extension model differs from Pi. Pi is great for a lot of things but has a larger memory footprint and start time than this claims to have so it would be interesting to compare the two.

Related: 3code is a coding agent (agentic loop) written in Nim (binary size: 1.6MiB): https://3code.capocasa.dev/

I don’t want another coding agent. I would have to be unemployed to try all new software that pops up everywhere. :)

And every says it is the one :)

I'm most impressed with the domain name. GG

I thought my `disc.sh` was good but this is better.

I'm sorry, but this is pure slop. This has 26 tools and a tool for every single file operation and a tool for read tool output? What the fuck... And they call this minimalist.... Lmfao

The person who built this obviously has little understanding of harnesses.

You should have significantly less tools today with how good LLMs have become.

The start up time and binary size are quite literally the most useless stats to base a harness off of lol

Man what with Cloudflare, Vercel and all these tech companies just releasing pure slop.

Just use Pi. It's actually minimal and well thought out by people who actually understand agents.

finally some good sofware

I too was frustrated with needing npm and slow startups or huge rust compile times for agents. I tried getting agents to write a tool like this with proper raw mode content pasting/ interruptions, but they just kept screwing it up without a framework like ratatui, so I wrote one in c by hand https://gist.github.com/fourlexboehm/a60e4ef9306744483731cd1... the only dependency is libcurl.

This binary is ~40kb and uses much less ram than fx.

I was wondering to build the same thing but someone already built it. I just need some agent that open/close super fast and don't eat half a gb of memory.

fx isn’t primarily “another coding agent.” It’s a tiny, embeddable agent harness and infrastructure component that also happens to have a good CLI.

Nice to see herdr support. The docs seem to imply it only works with vercel’s AI gateway? I guess it cant be configured to use another provider?

Is Vercel so all-in on Zig elsewhere too?

Just another CLI? You could simply fork one existing, rename it, and save tokens

Some questions:

1. Why do we need yet another coding agent over the rest of them?

2. Is this going to be another Vercel Labs slop project that they will abandon like the others since this is super experimental?

[dead]

[flagged]

[dead]

[dead]

[dead]

[dead]

i think there is a name clash here, i like fx the json viewer https://github.com/antonmedv/fx (20.6k star on gh)