Latest Open Source Projects
open-operator
open-operator
TLDR: This is a proof of concept. It requires pnpm for installation. Users need to set up API keys like OpenAI API key, Browserbase API key and project ID. It has a simple agent loop calling Stagehand and Browserbase. Key technologies include Browserbase, Stagehand, Next.js and OpenAI. Contributions are welcome and it's licensed under MIT.
yapsearch
yapsearch
TLDR: The project yapsearch aims to add search and reasoning capabilities to the agent within yapthread (app.yapthread.com).
Riona-AI-Agent
Riona-AI-Agent
TLDR: Riona-AI-Agent is an AI-powered automation tool for Instagram. It can generate engaging content, automate interactions like posting, liking, and commenting. Also supports proxy and cookie management. Future features include Twitter and GitHub automation.
geminiCoder
geminiCoder
TLDR: A project that generates small apps with one prompt powered by the Gemini API. It uses technologies like Gemini API, Sandpack, Next.js app router with Tailwind. Can be cloned and run locally.
openai-structured-outputs-samples
openai-structured-outputs-samples
TLDR: A repository of sample apps demonstrating the use of OpenAI's Structured Outputs feature with NextJS.
company-researcher
llama-ocr
llama-ocr
TLDR: An npm library for free OCR using Llama 3.2 Vision. It can handle local and remote images. Has a hosted demo and a roadmap for adding PDF support and JSON output.
logocreator
logocreator
TLDR: An open source logo generator that creates professional logos in seconds using customizable styles. It uses Flux Pro 1.1 on Together AI for logo generation, Next.js with TypeScript for the app framework, Shadcn and Tailwind for UI components and styling, Upstash Redis for rate limiting, Clerk for authentication, and Plausible & Helicone for analytics and observability. Future tasks include creating a dashboard with logo history, supporting SVG exports, adding more styles, adding an image size dropdown, showing approximate price with a custom Together AI key, allowing reference logo upload, and redesigning popular brand logos in a showcase.
Roo-Cline
Roo-Cline
TLDR: Roo-Cline is a fork of Cline, an autonomous coding agent. It comes with additional experimental features such as drag and drop images, sound effects, language selection, and support for various models. It provides capabilities like creating and editing files, running commands in the terminal, using the browser, and adding custom tools through the Model Context Protocol.
newsnow
newsnow
TLDR: An elegant news reading application that provides a pleasant reading experience with features like Github login and data synchronization. Supports deployment on Cloudflare Pages, Vercel and Docker.