The MySQL ODBC driver is what keeps BI tools, reporting systems, and ETL pipelines connected to MySQL without errors. Teams have depended on it for years, and it’s still vital today, especially...

An open-source testing platform and SDK for LLM and agentic applications that generates test scenarios and evaluates model outputs.

An open-source toolkit for MCP development and debugging that bundles a VS Code plugin, debugging panels, and an SDK to streamline the path from testing to deployment.

An open-source WebSocket server that wraps the Claude Agent SDK to enable real-time, bidirectional communication with Claude in sandboxes or local environments.

An open-source platform for retrieval-augmented generation (RAG) that simplifies multi-format ingestion, partitioning, and citation-aware retrieval.

An open-source web crawling and spidering framework by ProjectDiscovery focused on high concurrency, modularity, and integration with security tooling.

An open-source, stateless command-line tool providing quick question answering and a single-step agent mode.

An open-source project for automating documentation generation by combining content sources and model capabilities.

Analysis of closed-source model acceleration and open-source ecosystem response, exploring core engineering contradictions and infrastructure evolution.

An open-source model project that improves small-model reasoning via multi-stage distillation and optimization.

A TypeScript + React open-source component library for building customizable chat interfaces for AI assistants.

Learn five powerful open-source AI tools to boost your projects, save time, and stay ahead in AI innovation.

本研究评估了大型语言模型在提取出院报告关键信息中的有效性，发现模型可能产生幻觉，影响信息的可靠性，为改善患者护理提供了重要见解。

These models are free to use, can be fine-tuned, and offer enhanced privacy and security since they can run directly on your machine, and match the performance of proprietary solutions like o3-min...

A chatbot is a computer program that can talk to people.

本研究解决了开源语音模型缺乏合规数据的问题，聚焦欧盟24种官方语言。通过调查，收集了95万小时的训练数据，并发布了44.1万小时的自动转录数据，推动了开源语音模型的发展。

We’re excited to announce wildcard support across our Ruleset Engine-based products and our open-source wildcard crate in Rust. Configuring rules has never been easier, with powerful pattern...