Tag
The University of Hong Kong open-sourced the AutoAgent framework, which automatically builds and evolves multi-agent workflows via natural language with no code required, and includes a built-in deep research mode supporting multiple mainstream large models.
This open-source project can scrape web data with zero code, bypass anti-scraping mechanisms, boost efficiency tens of times, and has earned 50k+ stars.
Strava is tightening its API access by requiring a paid subscription for developers, citing a 448% increase in developer applications due to zero-code AI tools and scraping attempts that degrade platform performance.
A developer built a zero-code visual MCP client within AgentSwarms that allows testing remote MCP servers directly in the browser, demonstrated with Cloudflare's free MCP server for documentation.
MetaChain is a fully-automated, natural language-based framework that lets non-technical users create and deploy LLM agents without coding, showing strong results on the GAIA benchmark and RAG tasks.