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
LTX-2.5 – LTX's Open-Source AI Video Generation Foundation Model
LTX-2.5 is a professional-grade AI video generation foundation model open-sourced by Lightricks, an Israeli AI company. With 220 billion parameters, it provides full model weights upon release. The mo...
PixelRAG – Berkeley's Open-Source Vision-Native RAG Framework
PixelRAG is an open-source vision-native RAG framework developed by Berkeley's SkyLab/BAIR. It moves beyond the traditional RAG paradigm of extracting text from web pages or PDFs for retrieval, instea...
LTX-2.5 – Lightricks' Open-Source AI Video Generation Base Model
LTX-2.5 is a professional-level AI video generation base model open-sourced by the Israeli company Lightricks. With 22B parameters, the model weights are made available immediately upon release. It su...
Palmier Pro – Open-Source AI Video Editor That Generates Video and Images During Editing
Palmier Pro is a macOS-native video editor built from scratch using Swift, designed for the AI era. It is open-source and offers its core features for free. Its key innovation lies in embedding genera...
IndexTTS-2.5: In-Depth Review of Bilibili's Open-Source Industrial-Grade Zero-Shot Voice Cloning Model
IndexTTS-2.5 is an industrial-grade zero-shot voice cloning model open-sourced by the Bilibili Index Speech team, with only 0.8B parameters. This model supports cross-lingual transfer across five lang...
DeepSeek Harness – DeepSeek's AI Agent Execution Framework
DeepSeek Harness is an AI agent execution framework launched by DeepSeek, based on the core concept of "Model + Harness = Agent." Through engineering modules such as context management, tool calling o...
Nemotron 3.5 Lightning – NVIDIA's Open-Source MoE Model
Nemotron 3.5 Lightning is an open-source Mixture-of-Experts (MoE) model with 30B parameters launched by NVIDIA, specifically optimized for multi-agent systems. The model employs a sparse activation ar...
HOMIE – An Open-Source Digital Human Video Generation Framework from The Hong Kong University of Science and Technology
HOMIE is an open-source digital human video generation framework developed by the Department of Computer Science and Engineering at The Hong Kong University of Science and Technology. It is built upon...
PAST-Bench – Princeton's Benchmark for Performance Attribution in Personal Agents
PAST-Bench is a benchmark introduced by Princeton University's team led by Mengdi Wang, specifically designed to evaluate the recursive self-improvement capabilities of personal AI agents. By comparin...
Shotcut – Open-Source Video Editing Software with Multi-Track Support
Shotcut is an open-source video editing software built on FFmpeg, offering completely free usage with no watermarks or time restrictions. The software supports direct editing of hundreds of audio and ...
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.