Lists (16)
Stars
Self-Hosted Plaform for Secure Execution of Untrusted User/AI Code
The open-source reactive database for app developers
Parse and evaluate MS Excel formula in javascript.
Convert jsons to typescript interfaces
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
Index your Gmail account to a SQLite DB and play with the data.
ragingwind / ai-chatbot-desktop
Forked from vercel/ai-chatbotA full-featured, hackable Next.js AI chatbot built by Vercel and Electron for Desktop
bazza/ui is a React component library with hand-crafted, powerful, modern components.
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser, Trae AI & Cluely (And other Open Sourced) System Prompts, Tools & AI Models.
An open protocol enabling communication and interoperability between opaque agentic applications.
AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.
A zero-config, fast and small (~3kB) virtual list (and grid) component for React, Vue, Solid and Svelte.
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
A custom provider for the Vercel AI SDK that enables integration with models that use Azure's native API instead of the OpenAI API format
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
A starter kit for building ai agents on Cloudflare
🧰 Lightweight libraries for backends. Install one package, scale to production. Just a library, no SaaS.
🔩 The open-source serverless platform. Easily deploy & scale AI agents, complex workloads, and backends — all on a frictionless platform that runs anywhere.
This repository contains the Hugging Face Agents Course.
Generate Zero schemas from Drizzle ORM schemas.
Lightweight Durable TypeScript Workflows
Easily fine-tune, evaluate and deploy Qwen3, DeepSeek-R1, Llama 4 or any open source LLM / VLM!
streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL