OpenFic exists to keep AI in a supporting role—adapting to your workflow and lore—rather than auto-generating a finished manuscript.
App Builders
underdogs · picking up speedIt transforms scripts into consistent, AI-generated video sequences so teams don't have to manually prompt-engineer every scene.
Pre-built React components for conversations, messages, and reasoning displays that install via CLI into your codebase.
A component toolkit for building LLM interfaces without reinventing the chat bubble.
OpenUI gives LLMs a compact, streaming-first language to generate structured React interfaces directly, cutting token overhead and skipping the JSON middleman.
BitFun is a Rust-based runtime shipping four built-in agents—code, cowork, computer-use, and personal assistant—meant to run locally and stay running.
MoneyPrinter automates YouTube Shorts from a text topic, using local Ollama models to write scripts and a Dockerized queue to keep rendering reliable.
Cloudflare built this so its own workforce—from engineers to sales—could safely let AI agents write, run, and modify private sandboxed apps without trusting central SaaS or letting agents run unsupervised.
A CLI generator that spits out complete FastAPI + Next.js AI apps with agents, RAG, auth, and billing wired in.
Open CoDesign turns text prompts into prototypes, slides, and PDFs using whichever LLM you already pay for, without leaving your laptop.
A provider-agnostic, framework-native TypeScript SDK for streaming chat, tools, and multimodal AI with adapters for nine providers and six UI frameworks.
A deployable poster editor that mimics commercial design tools and keeps the entire stack—frontend, backend, and AI—in one repo.
LobsterAI puts a desktop AI agent to work on your actual machine—handling documents, data, and web tasks—then lets you boss it around from WeChat or Telegram.
LunaTranslator hooks into running visual novels—on PC or emulated console—to extract and translate text in real time, so you don’t need fan patches.
Ptero bundles access to several large language models behind a privacy-first interface that stores every conversation locally and runs without accounts or subscriptions.
It turns DeepSeek's chat interface into a studio for generating, refining, and exporting actual editable designs and slides.
HermesOffice replaces the bolted-on AI chat panel with a local agent that collaborates inside your documents and preserves untouched bytes.
This ComfyUI node turns the official MiniMax H3 pipeline into a multi-segment editing bay for long-form video with stitched motion and native stereo audio.
nurb lets you describe a part in plain English, then has your existing AI model it, check it against print physics, and hand you a slicer-ready file.
Maestro is a local creative suite that uses a built-in LLM to plan, shoot, and edit multi-clip music videos and short films without sending anything to the cloud.



