Vercel Open Sources fx Native Coding Agent

August 21, 2026
Vercel Labs has open sourced fx, a native coding agent and command line tool written in Zig for research and embedding in larger systems.
Vercel Open Sources fx Native Coding Agent

Vercel Labs has open sourced fx, a native coding agent that began as an internal tool. fx is a harness and command line interface written in Zig for research use and for embedding inside larger systems.

The tool is distributed as a single native binary with no runtime install. The announcement states that it cold starts in 10 microseconds, has a 6.3 MiB binary, and uses single digit megabytes of memory at baseline.

fx is model and provider agnostic and supports local and cloud inference. Its core can be extended through skills, plugins, and MCP. It can be used directly through the command line or embedded as infrastructure, with structured output, editor connections, and WebAssembly support for running in a browser.

The project is released under the Apache 2.0 license. The announcement states that fx has no product telemetry, keeps sessions and usage local, and shares source code or prompts only with the inference endpoint. Vercel Labs described fx as experimental and said frequent changes should be expected.

We hope you enjoyed this article.

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

Subscribe to AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Whitepaper

Governing the Future: A Strategic Framework for AI Adoption in Financial Institutions

This whitepaper explores the transformative impact of artificial intelligence on the financial industry, focusing on the governance challenges and regulatory demands faced by banks. It provides a strategic framework for AI adoption, emphasizing the importance of a unified AI approach to streamline compliance and reduce operational costs. The document offers actionable insights and expert recommendations for banks with fewer than 2,000 employees to become leaders in compliant, customer-centric AI.

Read more