fx
AIVercel Labs' tiny open-source coding agent — a ~6 MB native CLI written in Zig, built for speed, embeddability and Unix-style ergonomics.
fx
Vercel Labs' tiny open-source coding agent — a ~6 MB native CLI written in Zig, built for speed, embeddability and Unix-style ergonomics.
About fx
fx is a coding agent harness and command-line tool written in Zig, originally an internal Vercel Labs tool and open-sourced under Apache-2.0 in August 2026. It is built around minimalism: a roughly 6 MB single binary, a 10-microsecond cold start, a single-digit-megabyte memory baseline, and a deliberately small system prompt and tool set to keep token costs and time-to-first-token low. Rather than presenting a heavy 'IDE in the terminal' TUI, fx behaves like a Unix shell — preserving scroll history, producing minimal output, and avoiding complex repainting — which makes it comfortable to pipe, script and embed. It is model- and provider-agnostic, working with local models, gateways, direct provider APIs or existing subscriptions, and extends through skills, plugins and MCPs. Optimal WebAssembly builds from the Zig toolchain make the network stack pluggable and let the whole agent run inside a browser, which is how the live demo on the site works.
Screenshots
Key Features
Use Cases
Frequently asked questions about fx
What is fx?
Vercel Labs' tiny open-source coding agent — a ~6 MB native CLI written in Zig, built for speed, embeddability and Unix-style ergonomics.
How does fx work?
fx works by combining Tiny Native Binary: The whole agent ships as a roughly 6 MB executable designed for instant installation and for embedding in resource-constrained environments and agent sandboxes., Instant Time to Prompt: fx cold starts in about 10 microseconds and performs no unnecessary work or I/O before accepting user input, which matters for programmatic invocation., Minimal Memory Footprint: A single-digit-megabyte memory baseline lets you pack many concurrent instances onto one machine., Shell-Like Ergonomics: Scroll history is preserved by default and output is deliberately sparse, so the CLI composes like a Unix tool instead of taking over the terminal., Context Efficiency: A minimal system prompt and tool surface reduce token spend and improve time-to-first-token performance. to help users with Sandboxed Agent Execution: Ship a full coding agent inside a container or sandbox where a large runtime would not fit., Embedding in Larger Systems: Use fx as the agent harness inside your own product or internal platform rather than building a loop from scratch., CI and Scripted Automation: Invoke a coding agent from pipelines and scripts where fast cold starts and quiet output matter more than an interactive UI., Agent Harness Research: Experiment with system prompt and tool design on a deliberately minimal, readable Apache-2.0 codebase., Local-Model Coding: Run agentic coding against a locally hosted model without any dependency on a specific cloud provider..
What are the main features of fx?
Key features include Tiny Native Binary: The whole agent ships as a roughly 6 MB executable designed for instant installation and for embedding in resource-constrained environments and agent sandboxes., Instant Time to Prompt: fx cold starts in about 10 microseconds and performs no unnecessary work or I/O before accepting user input, which matters for programmatic invocation., Minimal Memory Footprint: A single-digit-megabyte memory baseline lets you pack many concurrent instances onto one machine., Shell-Like Ergonomics: Scroll history is preserved by default and output is deliberately sparse, so the CLI composes like a Unix tool instead of taking over the terminal., Context Efficiency: A minimal system prompt and tool surface reduce token spend and improve time-to-first-token performance..
Who is fx for?
fx is useful for anyone interested in Sandboxed Agent Execution: Ship a full coding agent inside a container or sandbox where a large runtime would not fit., Embedding in Larger Systems: Use fx as the agent harness inside your own product or internal platform rather than building a loop from scratch., CI and Scripted Automation: Invoke a coding agent from pipelines and scripts where fast cold starts and quiet output matter more than an interactive UI., Agent Harness Research: Experiment with system prompt and tool design on a deliberately minimal, readable Apache-2.0 codebase., Local-Model Coding: Run agentic coding against a locally hosted model without any dependency on a specific cloud provider..
How much does fx cost?
fx is free to use.
How do I get started with fx?
Visit https://fx.sh/ to sign up and explore fx.
Explore more AI Ai Agents tools
Browse all Ai Agents tools →Browse by use case: Code Generation
Compare fx: vs Apache Maka · vs Construct Computer · vs ShogunAI · vs OneCLI