Records found: 11
'Google released an experimental Python MCP server that exposes read-only Google Ads API tools (search via GAQL and list_accessible_customers) for LLM agents to query campaign data without custom SDKs.'
'ShinkaEvolve couples LLM-driven mutations with evolutionary search to evolve programs with far fewer evaluations, hitting SOTA on circle packing in about 150 evaluations and improving solutions across multiple domains.'
'IBM released Granite-Docling-258M, a 258M-parameter open-source document AI that preserves layout and improves OCR, table, code, and equation extraction for enterprise pipelines.'
'BentoML launched llm-optimizer to automate benchmarking and tuning of self-hosted LLMs and published a browser-based LLM Performance Explorer with pre-computed results.'
'Hugging Face released AI Sheets, a free open-source no-code spreadsheet that integrates with open-source LLMs for building, cleaning, and enriching datasets, available in-browser or for local deployment.'
'dots.ocr is an open-source 1.7B vision-language model that unifies layout detection and OCR to deliver state-of-the-art multilingual document parsing, including accurate table and formula extraction.'
Trackio is a free, open-source Python library that simplifies experiment tracking in machine learning by providing local-first data storage, seamless Hugging Face integration, and easy sharing via online dashboards.
Microsoft has open-sourced the GitHub Copilot Chat extension for VS Code, making its advanced AI coding features freely available to all developers under the MIT license.
DeepSeek researchers released nano-vLLM, a compact and efficient Python implementation of the vLLM engine that balances simplicity with performance for LLM inference.
ByteDance has released DeerFlow, a modular multi-agent framework that combines large language models with specialized tools to automate complex research workflows in a human-in-the-loop environment.
JetBrains has open-sourced Mellum, a 4-billion-parameter language model specialized for programming tasks, aiming to improve AI-assisted software development.