AI Model Library: LLMs, Agents & Dev Tools

Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.

Expert analysisUpdated regularlyRSS Feed

Latest Articles

Total 467 articles

3 months ago

Agora-1 – Odyssey's First Multi-Agent World Model

Agora-1 is Odyssey's first multi-agent world model, breaking past the single-user limits of traditional world models by enabling humans and AI to interact in the same real-time generated world simulat...

AI AgentEmbodied AIBenchmark
Jun 21, 2026Read more →
3 months ago

Xiaomi Auto World Model – Xiaomi's Assisted-Driving World Model

Xiaomi Auto's assisted-driving world model (Xiaomi Auto World Model) is the first to deeply couple 3D reconstruction (WorldRec) with video generation (WorldGen) into one driving-scene understanding an...

Video AIModel Inference
Jun 21, 2026Read more →
3 months ago

Webwright – Microsoft’s Terminal-Native Web Agent Framework

Webwright is Microsoft Research’s open terminal-native web agent framework—~1,000 lines of harness letting models write Playwright scripts, run bash, read logs, and iterate until complex browser jobs ...

AI AgentAI CodingModel Inference
Jun 21, 2026Read more →
3 months ago

WBench – Meituan’s Interactive Video World Model Multi-Turn Benchmark

WBench is Meituan LongCat’s first systematic multi-turn benchmark for interactive video world models—289 test cases, 1,058 interaction rounds, six scene types (nature, city, indoor, workspace, fantasy...

Video AIModel InferenceBenchmark
Jun 21, 2026Read more →
3 months ago

Wall-OSS-0.5 – X Square Robot’s Open Embodied Intelligence Model

Wall-OSS-0.5 is X Square Robot’s open vision-language-action (VLA) model—a 4B-parameter stack on a 3B Qwen2.5-VL backbone achieving zero-shot real-robot deployment without per-task fine-tuning. Gradie...

MultimodalEmbodied AIOpen Source
Jun 21, 2026Read more →
3 months ago

VitaBench 2.0 – Meituan LongCat’s Long-Horizon Dynamic Agent Benchmark

VitaBench 2.0 from Meituan’s LongCat team is the first benchmark for long-horizon dynamic user modeling in real-life agent scenarios. It ships 56 statistically grounded synthetic users, 819 lifecycle-...

AI AgentModel InferenceLLM
Jun 21, 2026Read more →
3 months ago

U2 – Unisound’s Native Agent Foundation Model

U2 is Unisound’s native agent foundation model for individuals, developers, and organizations—266B parameters delivering performance in the class of ~1.2T models under the mantra “high intelligence de...

AI AgentSpeech AIAI Coding
Jun 21, 2026Read more →
3 months ago

turbovec – Google's Open Vector Index Library

turbovec is a high-performance vector index library open-sourced by Google Research, implementing the TurboQuant algorithm. Written in Rust with Python bindings, it targets RAG workloads. Data-agnosti

LLMOpen Source
Jun 21, 2026Read more →
3 months ago

Toonflow – Open-Source All-in-One AI Short-Drama Creation Tool

Toonflow is an open-source, multi-agent platform that turns novels or creative text into structured scripts, storyboards, character visuals, and animated video—full pipeline from words to finished sho...

AI AgentVideo AIAI Coding
Jun 21, 2026Read more →
3 months ago

SwarmFlow – openJiuwen’s Open Multi-Agent Workflow Orchestration Framework

SwarmFlow is openJiuwen’s open-source framework for controllable multi-agent workflow orchestration. Its core idea separates orchestration from reasoning: collaboration flows run as predefined scripts...

AI AgentModel InferenceTool Calling
Jun 21, 2026Read more →
Page 35 of 47 (467 articles total)

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.