AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Latest Articles
Total 467 articles
LongCat-2.0 – Meituan's Open-Source Next-Generation Trillion-Parameter Language Model
LongCat-2.0 is Meituan's open-source next-generation large-scale MoE language model, with 1.6 trillion total parameters and approximately 48 billion activated parameters per token. It was fully traine...
Agent-Reach – Open Source AI Agent Tool for One-Click Internet Content Retrieval
Agent-Reach is an open-source, free AI Agent internet capability scaffolding tool designed to install web access for mainstream AI Agents such as Claude Code, Cursor, and OpenClaw with a single natura...
BrowserBC – An Open-Source Browser Operation Trajectory Generation Skill by Einsia AI
BrowserBC is an open-source project released by Navers Lab under Einsia AI. Its core goal is to transform human browser operation trajectories into reusable natural language skills, enabling Web Agent...
Penpot – Open Source Design & Code Collaboration Platform for Real-Time Multi-User Collaboration
Penpot is an open-source design and code collaboration platform built on open web standards such as SVG, CSS, and HTML. It runs entirely in the browser with no need to install any desktop client. It p...
HTML Anything – An Open-Source HTML Editor from the nexu-io Team
HTML Anything is an Agent-era HTML editor open-sourced by the nexu-io team. It comes with 75 built-in Skill templates covering 9 delivery formats including magazines, presentations, posters, and Xiaoh...
FastContext - Microsoft's Open-Source Lightweight Code Repository Exploration Model
FastContext is a lightweight code repository exploration model open-sourced by Microsoft Research, specifically designed for programming agents. This model completely decouples repository browsing fro...
GPT-5.6 – OpenAI's Latest Generation Large Language Model Series
GPT-5.6 is the latest generation large language model series launched by OpenAI. Due to regulatory requirements from the U.S. government, it is currently only available in a "limited preview" to a sel...
DSpark – Speculative Decoding Acceleration Framework Open-Sourced by DeepSeek and Peking University
DSpark is a speculative decoding acceleration framework jointly open-sourced by DeepSeek and Peking University, designed to address the core pain point of slow, "toothpaste-like" autoregressive genera...
Sakana Fugu – A Multi-Agent Orchestration System by Sakana AI
Sakana Fugu is a multi-agent orchestration system developed by Sakana AI, which dynamically schedules top-tier models through a single API to achieve emergent collective intelligence. The system features a built-in TRINITY evolutionary coordinator and a Conductor reinforcement learning orchestrator, automatically assigning roles such as thinker, executor, and verifier to different models without the need for manual workflow presets. Fugu supports recursive self-invocation and flexible model pool management, offering both Standard and Ultra editions. It achieves cutting-edge performance in rigorous benchmark tests, rivaling Fable 5 and Mythos Preview,...
MMSkills – A Multimodal Skill Framework Jointly Launched by Shanghai Jiao Tong University and Xiaohongshu
MMSkills is a multimodal skill framework jointly developed by Shanghai Jiao Tong University and Xiaohongshu, specifically designed for general-purpose visual agents. This framework extends traditional...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.