Nutlope/twitterbio

Generate your Twitter bio with AI

What it solves

Writing a Twitter (X) bio is often a blank-page problem. This web app removes that friction by generating a full bio for you from a few inputs, using two large language models running on Together AI. It turns a short form into a ready-to-paste bio in seconds, without needing any AI expertise from the user.

How it works

You fill in a simple form with details about yourself or your profile (the README calls this "the form and user input"). The app constructs a prompt from that input and sends it to the Together AI API. The response is streamed back to the browser, so you see the text appear as it is generated. Two models are used: Qwen 3.5 9B (with thinking disabled for fast, direct answers) and GPT OSS 20B (a reasoning model that thinks before responding, shown with a "Thinking..." indicator while it works). The project is a Next.js app that runs locally with a single environment variable for your Together AI API key, and can also be deployed to Vercel with one click.

Who it's for

Anyone who needs a Twitter (X) bio quickly — individuals, creators, developers, or professionals who want a polished bio without spending time writing it. It's also useful for developers who want to see a concrete example of building a streaming AI-powered web app with Together AI and Next.js.

Highlights

  • Uses two different AI models (Qwen 3.5 9B and GPT OSS 20B) to generate bios, with streaming output for a live typing effect.
  • Simple one-page interface: fill in a form, get a complete bio.
  • Requires only a Together AI API key to run locally (npm run dev after setting the key in a .env file).
  • One-click deploy to Vercel is provided, making it easy to launch your own instance.

Related

  • Project
    mylxsw/aidea-server

    AIdea Server is an open‑source Go backend that aggregates chat‑style LLMs and image‑generation models behind an OpenAI‑compatible API, adding user accounts, token‑based billing, notification bots, and auxiliary AI services. It can be self‑hosted (binary or Docker) and integrates with MySQL, Redis, and various cloud providers.

  • Project
    yincongcyincong/MuseBot

    MuseBot is a chatbot that connects eight popular messaging platforms (Telegram, Discord, Slack, Lark, DingTalk, WeChat Work, QQ, and WeChat) to large language models such as OpenAI, DeepSeek, and Gemini, enabling AI-powered responses with support for images, documents, voice, function calling, and RAG. It can be deployed locally or via Docker in about a minute.

  • Project
    amitshekhariitbhu/llm-internals

    LLM Internals is a free, growing series of blogs and videos (linked from a README) that teaches how large language models work internally—from tokenization, attention math, and transformer architecture to inference optimizations like KV Cache, Flash Attention, and Speculative Decoding. Created by Amit Shekhar, founder of Outcome School.

  • Project
    lyra81604/zhengxi-views

    An AI Agent Skill that provides a traceable, evidence-based knowledge base of fund manager Zheng Xi's investment views and methodology to prevent AI hallucinations in financial analysis.