プログラミング
fx: 小さく、オープンで、ネイティブなコーディングエージェント
fx :Tiny, open, native coding agent. (fx.sh)
要約
fxは、Zigで書かれた小さく(約6MB)、高速で、オープンソースのコーディングエージェントおよびCLIツールです。WebAssemblyをサポートし、リソースが限られた環境やエージェントサンドボックスへの組み込みに最適化されています。研究や大規模システムへの統合を目的としており、モデルやプロバイダーに依存しない設計が特徴です。
全文翻訳
Tiny, open, native coding agent.$ curl -fsSL https://fx.sh/setup.sh | bashcopiedv0.0.3 · 6.39mib · status: experimental (i)use at your own risk, we will be making frequent changesThis demo runs the full fx CLI as WebAssembly compiled with the Zig toolchain.Networking is delegated to browser fetch, and every SDK aspect is configurable in the docs.fx𝒇x v0.0.3 · Run /help for commands ┃ auto · glm-5.2(i)This demo is available in browsers with WebAssembly JSPI support, like Safari 27+ and Chrome.This demo runs fx in WebAssembly with a browser workspace powered by just-bash. Install fx for the full tool suite on your own files.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.***Tiny ~6mb binaryDesigned for instant installation and embedding in resource constrained environments and agent sandboxes.Instant time to promptfx cold starts in 10µs and does no unnecessary work or I/O prior to accepting user input, making it ideal for programmatic use.Wasm supportOptimal fx.wasm builds produced by the Zig toolchain, which further reduce fx's size, making the network stack pluggable.Minimal memory footprintfx contributes single-digit megabytes of memory baseline, allowing you to pack many instances in one machine.Shell-like UI and ergonomicsfx preserves scroll history by default, produces minimal output, and makes sparing use of complex TUI or paintsContext efficientMinimal system prompt and tools, to save on token costs and to yield optimal time-to-first-token performance (TTFT).Embeddable and extensibleSmall core, extended via skills, plugins, MCPs, with a Unix-like philosophy to extensibility.Model and provider agnosticDesigned to work with local models, gateways, direct provider API access or subscriptions.