🚀@vercel's’ fx is a tiny open-source coding agent built to take action directly in a developer’s workspace. This demo extends that idea by giving fx access to the security policies, requirements, and release docs stored in Box. Using the Box CLI, fx retrieves an approved policy, compares it with local code, edits the files, adds missing test coverage, and prepares release evidence without being told which lines to change. It asks for human approval before uploading anything, then verifies every file after it lands in Box. Git stays where the code lives. Box stays where the approved docs and release proof live. fx connects the work across both. Demo below ↓

It's likely that more software will be produced next year than in all of the history of computing. It took Vercel 10 years to get to 1 billion deployments, but then we added another 1.4 billion in the last 10 months alone. Some of this will be tiny, personal and even disposable software. An HTML file with some javascript ("artifacts"), a report, a pricing calculator, a slide deck, all the way to sophisticated apps, agents and platforms. Deployment speed is one of our obsessions. We've brought down the time to deploy, upload, assign a domain and globally propagate an artifact to 1 second. This is quite a feat considering we serve these artifacts with uncompromising performance and security. This sub-second deployments include our global CDN, Firewall, immutable deployments, domain assignment, observability, rollbacks… And we're not done yet. Follow @melkeydev for more.

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

fx v0.0.10 Faster turn handling. Faster request starts. • Turn processing up to 1.6× faster in longer sessions • Model requests start up to 2.5× faster • Better recovery from shell failures • More reliable session resume & scrollback • Cleaner rendering across terminal widths • Stronger secret protection for MCP errors

can now orchestrate subagents with different models & reasoning efforts. e.g: Fable planning and Grok executing. Fable is a genius, Grok is a fast workhorse. ① Simple. 𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍 or your prompt can indicate this preference. ② Steer as you please. It’s extremely enjoyable to use. You just talk to the agent and interrupt at will. Worth noting this works with any model, any gateway. No fancy server-side routing. Just harnessing (no pun intended) the model’s intelligence and ability to orchestrate.

fx v0.0.9 Use a frontier model to steer, then hand implementation to a fast workhorse. • Give each subagent its own model and reasoning effort • Subagents keep working while you steer • Send feedback to subagents mid-task • Switch models with Ctrl+P without losing your draft or images • New conversations get short automatic titles • Better GitHub-style Markdown rendering • New libfx examples for Node.js, browsers, Next.js & Nuxt No new commands or concepts. Just chat with fx.

fx v0.0.8 Embedding fx just got much faster. • NAPI initialization is over 40× faster • Smaller, more accurate shell tool with 75% fewer actions • TUI up to 19.6× faster, with first paint 74.6× faster • Common CLI commands 18–25% faster • 2.8% smaller binary (6.01mib vs 6.19mib) • Active turns can now be steered with Enter We've also documented MCP integrations with @calcom , @clerk, @knocklabs, @plainsupport, @prisma, @sentry, @Stagehanddev, @upstash

fx v0.0.7 MCP now feels native to fx. • Added 𝚏𝚡 𝚖𝚌𝚙 commands • Project-level MCP configuration • MCP management from the CLI • Better compatibility with existing servers • Cleaner transcripts & live turn feedback • Steer active turns with Ctrl+Enter • 8 fewer tools for sharper choices & more context Documented integrations with @NotionHQ @huggingface @ExaAILabs Thanks to @biraj21_, AdrianTJ & ssynb