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

Tag: Tool Calling

45 article(s) found · Clear tag

2 months agoMultimodalDocument AITool Calling

SenseNova U1.5 Lite – A Lightweight Native Unified Multimodal Large Model Open-Sourced by SenseTime

SenseNova U1.5 Lite is a lightweight native unified multimodal large model open-sourced by SenseTime, specifically designed for real-world visual creation workflows. This model achieves a native multi...

Read more
SenseNova U1.5 Lite – A Lightweight Native Unified Multimodal Large Model Open-Sourced by SenseTime cover image
2 months agoAI AgentAI CodingTool Calling

Codex Harness – OpenAI's Open-Source AI Agent Execution Framework

Codex Harness is an open-source AI Agent execution framework developed by OpenAI, positioned as the "exoskeleton" system that drives AI agents. It manages the complete execution cycle, including task ...

Read more
Codex Harness – OpenAI's Open-Source AI Agent Execution Framework cover image
2 months agoAI AgentTool CallingBenchmark

HarnessEval – The Evaluation System Jointly Launched by MirroS, Tsinghua University, Peking University, and NVIDIA

HarnessEval is an agentic evaluation system jointly developed by MirroS with top institutions such as Tsinghua University, Peking University, UC Berkeley, MIT, and NVIDIA. This system agentifies the e...

Read more
HarnessEval – The Evaluation System Jointly Launched by MirroS, Tsinghua University, Peking University, and NVIDIA cover image
2 months agoAI AgentAI CodingTool Calling

Nature Skills – Open-Source AI Research Skill Library, Focused on the Full Paper Workflow

Nature Skills is an open-source skill library designed for AI scholars and researchers worldwide, focusing on assisting with the full workflow of writing and submitting papers at the Nature / CNS leve...

Read more
Nature Skills – Open-Source AI Research Skill Library, Focused on the Full Paper Workflow cover image
2 months agoAI CodingEmbedding & RAGTool Calling

ToolJet – Open-Source AI Low-Code Development Platform for Visual Drag-and-Drop App Building

ToolJet is an open-source low-code development platform designed to replace commercial low-code tools such as Retool. It provides over 60 draggable components and more than 80 data source connectors, ...

Read more
ToolJet – Open-Source AI Low-Code Development Platform for Visual Drag-and-Drop App Building cover image
2 months agoAI AgentTool CallingEdge Deployment

DSH Desktop – Open-Source DeepSeek Harness Desktop Application

DSH Desktop is the open-source desktop client for DeepSeek Harness, packaging it as a locally optimized desktop application. It supports macOS and Windows, allowing users to launch it with a single cl...

Read more
DSH Desktop – Open-Source DeepSeek Harness Desktop Application cover image
2 months agoAI AgentAI CodingTool Calling

Grok Bot: In-Depth Review of the Cloud-Resident, Multi-Bot Collaborative AI Agent System

Grok Bot is an AI Agent system launched by SpaceXAI, whose core capability lies in simulating human operational behavior to directly log in and control various websites and applications at the interfa...

Read more
Grok Bot: In-Depth Review of the Cloud-Resident, Multi-Bot Collaborative AI Agent System cover image
2 months agoSpeech AIVideo AITool Calling

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...

Read more
LTX-2.5 – Lightricks' Open-Source AI Video Generation Base Model cover image
2 months agoAI AgentAI CodingTool Calling

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...

Read more
DeepSeek Harness – DeepSeek's AI Agent Execution Framework cover image
2 months agoModel InferenceLLMTool Calling

Ling-3.0-tiny – Ant Ling's Native Hybrid Inference Model

Ling-3.0-tiny is a native hybrid inference model introduced by the Ant Ling team, utilizing a sparse mixture-of-experts architecture (MoE). With a total of 7.9B parameters, it activates only 1.3B para...

Read more
Ling-3.0-tiny – Ant Ling's Native Hybrid Inference Model cover image
Page 3 of 5 (45 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.