Vercel Releases Programming Agent Called fx
Vercel has introduced a new programming agent named fx, which boasts a small size and high launch speed.
Vercel Releases Programming Agent Called fx
Vercel has unveiled its new programming agent called fx. This agent goes against the current trend, weighing only 6.3 MB and launching in about 10 microseconds.
fx is written in Zig and distributed as a single standalone file. It does not require Node.js, Python, or other runtime environments, and can be connected to any model—local or cloud-based.
Thanks to its minimalist architecture, fx is suitable for:
- sandboxes
- model testing
- quality assessment
- training
- internal product infrastructure.
There is even a version for WebAssembly, which weighs less than the main build: fx.sh/try.
The source code is open.
Why it matters
AnalysisThis new agent can significantly simplify the programming and testing of models due to its lightweight and fast nature. It opens up new possibilities for developers in creating and implementing AI solutions.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Claude Code Guide: Setup for Agentic Programming (Beginner-Friendly)
A comprehensive practical guide to setting up Claude Code: CLI installation, CLAUDE.md and settings.json configuration, permission matrices, automated hooks, custom /truth command, and subagents.
Loop Engineering: Architecture of Autonomous Agentic Loops and the Post-Prompting Era
A deep dive into Loop Engineering: self-sustaining execution loops for Claude Code and autonomous agents, the DOER/CHECKER topology, deterministic verification, the /goal primitive, and reward hacking mitigation.
Short-Term and Long-Term Memory of Agents
The architecture of multi-tier memory for autonomous agents. It distinguishes between Short-Term Memory (active context window of the current session) and Long-Term Memory (vector databases, user profile files, and episodic diaries).
Thinking Machines Releases Inkling 2 Small: a 594B MoE Model That Can Fine-Tune Other Models
Thinking Machines released Inkling 2 Small, a 594B-parameter MoE model that leads among open models in several benchmarks and demonstrated autonomous fine-tuning of Qwen3.5-4B.