1671 related articles
ResearchPrompt engineering optimizations for coding Agents reduce tool calls, lower output tokens, and improve completion speed by 3-10%—delivering significant cost savings and latency reduction at scale.
Tech FrontiersDeepSeek releases V3.2-Exp with proprietary DeepSeek Sparse Attention (DSA) for faster long-context training and inference, plus API prices cut over 50%.
Tech FrontiersExplore how simulation solves AI testing challenges, covering scenario simulation, large-scale regression testing, and multi-agent verification to build reliable AI systems.
Product ReviewsIn-depth review of MiroFlow open-source AI workflow framework: technical architecture behind 5+ benchmark Top-1 rankings, multi-model support, Web UI, and comparison with LangChain and Dify.
Product ReviewsDeep dive into Opik: an open-source platform for LLM app lifecycle management with tracing, automated evaluation, hallucination detection, and production monitoring for RAG and Agent workflows.
Product ReviewsDeep dive into Opik: an open-source platform for LLM app lifecycle management with tracing, automated evaluation, hallucination detection, and production monitoring. 19K+ GitHub stars.
Product ReviewsDeep dive into LiteLLM, the open-source AI gateway supporting 100+ LLM APIs with a unified OpenAI format. Covers core features, usage modes, and enterprise use cases.
TutorialsDeep dive into the open-source project system-prompts-and-models-of-ai-tools: 7000+ lines of system prompts from ChatGPT, Claude & more, covering prompt engineering best practices and safety design.
TutorialsDeep dive into the E-commerce-Smart-Agent open-source framework built with LangGraph and FastAPI, covering RAG knowledge base Q&A, return workflow automation, and graph-based orchestration.
Product ReviewsFay is an open-source Agent framework with 12,700+ GitHub Stars, connecting digital humans, LLMs like DeepSeek, and enterprise systems for customer service, virtual streaming, and more.
Product ReviewsIn-depth review of Agentica, an open-source AI Agent framework featuring async-first architecture, tool calling, RAG, multi-agent collaboration, and MCP protocol support, with comparisons to LangChain and other mainstream frameworks.
TutorialsA deep dive into Nous Research's Hermes Agent open-source AI framework and the community Orange Book guide covering tool calling, reasoning, multi-Agent collaboration, and more.
Deep DivesDeep analysis of Claude Code's source architecture: Agent loop mechanism, context engineering strategies, tool system design, and permission controls. Based on the viral GitHub project how-claude-code-works.
Product ReviewsDeep dive into Datus-agent, an open-source AI-native CLI SQL client that brings Context Engineering to data engineering with natural language queries and modern data stack support.
TutorialsA deep dive into Context Engineering: core concepts and key techniques including RAG, long-context management, and AI Agent context orchestration for building production-grade AI systems.
Product ReviewsDeep dive into ByteDance Volcengine's open-source MineContext — a proactive context-aware AI assistant. Explore Context Engineering, ChatGPT Pulse integration, and real-world applications.
TutorialsDeep dive into the 15K-star GitHub project Agent-Skills-for-Context-Engineering, covering context engineering fundamentals, multi-agent architecture patterns, and production-grade Agent system best practices.
Deep DivesDeep analysis of the 10K-star GitHub project claude-code-system-prompts, fully deconstructing Claude Code's system prompts, 24 built-in tools, and sub-agent architecture for prompt engineering and AI Agent development.
Product ReviewsIn-depth analysis of SwarmUI, a C#-based modular Stable Diffusion web interface. Compare it with AUTOMATIC1111 and ComfyUI, exploring its high-performance architecture, modular extensions, and usability design.
TutorialsA detailed guide to ComfyUI-WanVideoWrapper: integrate Wan video generation models into ComfyUI with text-to-video and image-to-video workflows, VRAM optimization tips, and use cases.