5086 related articles
Deep DivesExplore Hugging Face Transformers, the 160K-star open-source AI framework powering text, vision, audio, and multimodal models with elegant APIs and massive community support.
Product ReviewsDeep dive into awesome-LLM-resources, a GitHub 8K+ star project offering the most comprehensive LLM learning resources covering Agents, MCP, multimodal AI, and more.
Product ReviewsUnsloth is an open-source tool with 63K+ GitHub stars that provides a Web UI for locally training and running LLMs like Gemma 4, Qwen3.6, and DeepSeek.
Product ReviewsExplore awesome-agent-skills, a comprehensive GitHub resource with 4500+ stars featuring tutorials, guides, and skill catalogs for AI Agent development.
Product ReviewsClawCode is an open-source coding agent CLI built with Python and Rust, supporting 200+ AI models with experience-based evolution capabilities.
Product ReviewsCowAgent is an open-source super AI assistant powered by LLMs with 44K GitHub Stars, supporting WeChat, Feishu, DingTalk with agent capabilities.
Tech FrontiersCodex CLI 0.128.0 introduces the /goal command, enabling auto-looping task execution until objectives are met or token budgets are exhausted.
Product ReviewsAxonHub is an open-source AI gateway built in Go that lets developers use any SDK to call 100+ LLMs with failover, load balancing, and cost control.
Product Reviewsnanobot, an ultra-lightweight personal AI Agent from HKUDS, has gone viral on GitHub with 41K+ Stars. Learn why this minimalist framework is reshaping the AI Agent landscape.
Product ReviewsCC Copilot is an open-source desktop GUI for Claude Code, offering multi-AI provider switching, project management, and real-time token usage tracking.
Product ReviewsA deep dive into RuoYi-AI, a Java-based enterprise AI development platform supporting multi-vendor LLM integration, RAG knowledge bases, and agent orchestration. 5,200+ Stars on GitHub.
TutorialsMiniMind-V is a lightweight open-source VLM project that trains a 65M parameter vision multimodal model from scratch in just 2 hours. Learn its architecture, training pipeline, and educational value.
Product Reviewsawesome-pretrained-chinese-nlp-models is a 5500+ Star GitHub project indexing Chinese pre-trained models including BERT, ChatGLM, Qwen, and multimodal models, categorized by task, scale, and domain for efficient model selection.
Product ReviewsOpenYak is an open-source local AI agent supporting Windows/macOS/Linux. Access 100+ models via OpenRouter, MCP, and Ollama with BYOK zero-telemetry privacy — a strong alternative to Claude Code and OpenAI Codex.
Product ReviewsNadirClaw is an open-source, self-hosted LLM router that automatically routes simple tasks to cheap models and complex tasks to premium ones, saving 40-70% on AI API costs with OpenAI-compatible proxy support.
TutorialsSimon Willison built an iNaturalist observation display tool from scratch using his phone and Claude Code while camping. Full breakdown of the three-layer data pipeline architecture and AI-assisted mobile development workflow.
TutorialsSimon Willison used Claude Code for web on his phone to add iNaturalist wildlife sightings to his blog, going from prototype to production in one day.
Product ReviewsExplore claude-code-prompt-optimizer: an open-source tool using Hook interception and Claude Opus to auto-rewrite simple prompts into structured instructions, boosting Claude Code output quality.
Product ReviewsDeep dive into RuoYi-Vue-Pro: a 37K Star enterprise Java platform built on Spring Boot + MyBatis Plus + Vue, with multi-tenancy, workflows, CRM, ERP, and AI modules.
Product ReviewsDeep dive into Tencent Music's open-source Cube Studio cloud-native AI platform, covering distributed training, LLM fine-tuning, vLLM inference, VGPU virtualization, and Huawei Ascend adaptation.