Trending Open Source Projects
Discover trending open source projects with rapid star growth. AI summaries help you stay ahead of the curve.
Apple's MobileCLIP: Open-Source Mobile Vision Model
Apple’s MobileCLIP is a lightweight, zero‑shot image‑text model that runs on mobile devices with competitive accuracy. The open‑source GitHub repo contains training scripts, evaluation code, pretrained checkpoints, and a ready‑to‑run iOS app. It supports multiple MobileCLIP variants (S0 to S4, B, L‑14) and the newer MobileCLIP2 lineup, all integrated with OpenCLIP and HuggingFace. This article walks through the architecture, dataset preparation (DataCompDR, DFNDR), performance benchmarks against ViTs, quick‑start inference recipes, and how developers can extend or finetune the models for their own apps.
Lumina: Swift Camera Library for CoreML Integrated Imaging
Lumina is a lightweight, battle‑tested Swift framework that gives iOS developers an out‑of‑the‑box camera system with CoreML model streaming, QR/Barcode scanning, face detection, depth data and video capture. No AVFoundation boilerplate, just drop‑in view controller, sample app and a handful of API calls to get started. Whether you’re building a retail app with live product recognition or a photo journal with depth‑aware portraits, Lumina lets you focus on your business logic while handling low‑level camera plumbing for you.
ClawdBot One‑Click Install for Your AI Assistant
Discover how to turn your server into a smart personal assistant in minutes. ClawdBot’s installer bundles everything from multi‑model support to Telegram, Discord, WhatsApp, and more. Follow our step‑by‑step guide to deploy, configure, and secure your AI assistant with minimal effort – ideal for developers, hobbyists, and anyone eager to experiment with AI in a practical, hands‑on way.
Tokscale: Track AI Token Usage Across Multiple Platforms – CLI Tool
Discover Tokscale, the new open‑source CLI that lets developers monitor token consumption from OpenCode, Claude Code, Codex, Gemini, Cursor, Amp, and more. Learn how Tokscale’s real‑time pricing, leaderboard, and 2D/3D contribution graph help you gauge cost and efficiency. Step‑by‑step instructions guide you from installation with Bun to customizing filters, launching the interactive TUI, and exporting JSON data for dashboards. Whether you’re a freelancer or an enterprise team, Tokscale gives you instant insight into your AI usage and helps you optimize tokens, saving money and boosting productivity.
Qwen3-ASR: Alibaba’s Open‑Source 52‑Language ASR Model
Alibaba Cloud’s latest release, Qwen3‑ASR, brings state‑of‑the‑art multilingual speech recognition to the open‑source community. Supporting 52 languages and 22 Chinese dialects, the two 1.7B/0.6B models excel on benchmarks and rival commercial APIs. The repo ships with a full inference toolkit that works with transformers or the high‑performance vLLM backend, automatic timestamping via the Qwen3‑ForcedAligner, and a ready‑to‑run Gradio demo. Whether you’re a researcher, developer, or hobbyist, this guide walks you through downloading, setting up, benchmarking, and deploying Qwen3‑ASR in Docker or directly on GPU, so you can start transcribing speech, music, and songs with ease. Key highlights: multilingual support, streaming inference, forced‑alignment, quick‑start scripts, Docker deployments, and API integration with OpenAI‑compatible endpoints.
Run OpenClaw AI Assistant on Cloudflare Workers: A Step‑by‑Step Tutorial
Discover how to turn the open‑source OpenClaw AI assistant into a fully managed, always‑on chatbot running on Cloudflare Workers. This guide walks through prerequisites, secret setup, deployment, optional R2 persistence, authentication with Cloudflare Access, and even browser automation via CDP. By the end you’ll have a production‑ready, multi‑channel AI assistant that’s secure, scalable, and free from the hassle of self‑hosting.
PageIndex: The Open-Source Reasoning-Based RAG Framework
Discover PageIndex, a groundbreaking open‑source tool that eliminates the need for vector databases in Retrieval Augmented Generation (RAG). By building a hierarchical tree index and using LLM reasoning, PageIndex achieves human‑like retrieval without chunking or vector similarity. This article dives into its core concepts, installation steps, practical use cases—especially finance and legal document analysis—and its impressive benchmark results. Whether you’re a researcher, developer, or data scientist, learn how to transform long PDFs and markdown files into actionable knowledge with this lightweight Python library.
JJYB_AI VideoAutoCut: The Open Source AI Video Editing Toolkit
Discover JJYB_AI VideoAutoCut (v2.0), a complete AI‑powered video editing suite that automatically cuts, adds commentary, and applies AI voice‑over using 19 language models, 6 vision models, and 4 TTS engines—all wrapped in a simple Flask web interface. Learn how to install, configure, and deploy this Python‑powered solution on Windows or macOS and start creating professional videos with zero manual editing.
Karpathy's LLM Coding Rules: Think, Simplify, & Iterate
Discover Andrej Karpathy’s four‑principle guide to coding with Claude LLM. Learn how to think before you code, avoid over‑engineering, make surgical changes, and execute goal‑driven loops. The article explains each principle in depth, provides practical install instructions, and shows how to add the rules to your own projects for cleaner, more reliable code. Ideal for developers wanting to harness LLMs while keeping maintainability and clarity.
Feishu Channel Plugin for Clawdbot – Fast & Feature‑Rich
Looking to extend Clawdbot with Feishu (Lark) support? This article walks you through installing the @m1heng-clawd/feishu plugin, configuring the necessary App ID, App Secret, event subscriptions, and permissions on the Feishu Open Platform. It covers both WebSocket and webhook connection modes, DM and group policies, media upload/download, and the optional card‑rendering feature for rich markdown output. A full FAQ section tackles common pitfalls such as message reception failures, 403 errors, and how to start a new conversation with the /new command. Get your bot talking to Feishu users in minutes.