AI One-Shot Rust Rewrite of TerminalTextEffects: 43x Faster Startup
Melvin Vivas · X post · 2026-08-10 · Open on X
Topics: AI Dev Tools & Productivity, Industry Trends & Job Market · Level: intermediate
Summary
An AI model called Fable rewrote the Python library TerminalTextEffects in Rust in one shot, using 11M tokens. Startup time dropped from 87 ms to 2 ms and rendering got 9.6x faster. The result has zero dependencies and ships as a single 3 MB executable. Melvin's takeaway is that AI now makes performance rewrites practical.
Key points
- The whole TerminalTextEffects library was rewritten from Python to Rust in one shot, using 11M tokens.
- Startup time fell from 87 ms to 2 ms.
- Rendering speed improved 9.6x.
- The rewrite has zero dependencies and is a single 3 MB executable.
- Lesson: coding agents make rewriting libraries for speed much cheaper.
Resources mentioned
- Claude Code artifact: Rust rewrite of TerminalTextEffects · other · x.com · free
Shared Claude Code artifact showing the AI-generated Rust rewrite. - TerminalTextEffects · repo · github.com · free
Python library for visual text effects in the terminal; the original that was rewritten. - Fable · tool · anthropic.com · paid
Named as what the creator used with Devin for this build; the post gives no details about what it is.
Also in: Demo: One-Shotting a Flappy Bird iPhone App with Devin and Fable 5.1 (Melvin Vivas on X · notes), Subagents with mixed models: a strong planner and a fast executor (Melvin Vivas on X · notes), Cognition's SWE-2 Coding Model Now in Devin (Melvin Vivas on X · notes), GPT-6 Astra Access Across Plans vs Fable on Claude Max (Melvin Vivas on X · notes) and 10 more
Try this
- Use a coding agent to rewrite a slow Python CLI or library in Rust, and measure startup and runtime speedups.
More in AI Dev Tools & Productivity
- Grok access: X Premium+ isn't enough, you need SuperGrok
- ChatGPT Desktop App (with Codex) Now in Preview for Linux
- Cursor Tip: Use Canvas to Compare UI Design Variations Before Implementing
- Use Codex to set up and fix local tooling
- MiniMax H3 Image + Audio-to-Video Lip-Sync Demo (with Irodori-TTS v3)
- Generating AI Video Locally with MiniMax H3 in ComfyUI on an RTX 3090