1927 related articles
TutorialsComplete guide to Ollama: install and run DeepSeek, Qwen, Kimi-K2.5, GLM-5 and more LLMs locally. 170K+ GitHub Stars, the most popular local LLM framework for offline AI inference and privacy.
Tech FrontiersDeep dive into Osaurus — a native macOS AI agent framework supporting fully offline operation, persistent memory, cryptographic identity, and arbitrary model integration. Built with Swift and C for Apple Silicon. 5,100+ GitHub stars.
Tech FrontiersDeep dive into Anthropic's open-source claude-agent-sdk-demos project, covering Claude Code SDK core capabilities, TypeScript demos, multi-step task orchestration, and tool call integration for AI agent development.
TutorialsOpenAI Codex CLI 0.128.0 adds the /goal command for auto-looping task execution until goals are met. Learn about Ralph Loop pattern, token budgets, and autonomous coding agents.
Product ReviewsCodex is an open-source coding agent built in Rust that supports OpenAI, Anthropic, and Gemini models, offering developers a flexible multi-model AI programming tool.
Product ReviewsClawCode is an open-source coding agent CLI built with Python and Rust, supporting 200+ AI models with experience-based evolution capabilities.
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.
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.
Expert OpinionsAs vibe coding makes app development as easy as blogging, personalized micro-tools are proliferating. This article explores why RSS/Atom is the ideal solution for app discovery and distribution in the AI-assisted programming era.
Product ReviewsChatbox is an open-source AI client with nearly 40K GitHub Stars, supporting ChatGPT, Claude, Gemini and local models with cross-platform desktop apps, local data storage, and Prompt management.
Product Reviews9router is an open-source AI model routing tool aggregating 40+ free providers, supporting Claude Code, Cursor, Copilot and more with auto-failover and token compression for free unlimited AI model access.
Product ReviewsDeep dive into the 8,200-star awesome-LLM-resources GitHub project covering the full LLM lifecycle: data processing, training, inference, Agents, multimodal, and more.
Expert OpinionsAs vibe coding makes app development as frequent as blogging, we need lightweight mechanisms like RSS to discover and share personal AI tools. Exploring the future infrastructure of AI app distribution.
TutorialsDeep dive into Hugging Face Transformers: core features, multi-framework support, 500K+ pretrained models, full-modality task coverage, and hands-on code examples to build AI apps efficiently.
Tech FrontiersSimon Willison releases LLM 0.32a0 alpha with message sequence modeling and typed streaming parts, supporting multimodal output and conversation history injection while maintaining backward compatibility.
Tech FrontiersDeep dive into Codex CLI 0.128.0's new /goal command: how prompt templates drive autonomous agent loops, token budget controls, and AI coding agents that work until the goal is done.
Product ReviewsCyrus is an open-source AI programming agent supporting self-hosted deployment, integrating Linear, Slack, GitHub, and multiple AI models like Claude, Codex, and Gemini for secure automated coding workflows.
Expert OpinionsVibe Coding makes building apps as easy as blogging, but how are these personal micro-apps discovered? Matt Webb proposes RSS for distributing vibe-coded apps, and Simon Willison has already implemented it.
TutorialsDeep dive into Hugging Face Transformers: the open-source framework with 160K GitHub Stars. Covers full-modality model support, pipeline API, Hub ecosystem, and community mechanisms driving AI democratization.
Product ReviewsIn-depth review of Chatbox, an open-source AI client supporting unified access to GPT-4, Claude, Gemini and more. Covers core features, tech architecture, and comparisons with alternatives.