LlamaIndex 周报：LlamaAgents 早期访问上线，支持 Claude Sonnet 4.5

Hi there, Llama Enthusiasts! 🦙

Welcome to this week's edition of the LlamaIndex newsletter! We're excited to bring you updates including the launch of LlamaAgents early access, a full-stack agent template with CopilotKit, comprehensive TypeScript workflows documentation, and our latest tools. Check out these developments along with our community contributions to maximize your agent-building capabilities.

If you haven't explored LlamaParse yet, make sure to sign up and get in touch with us to discuss your specific enterprise use case.

Explore our free and paid plans today.

🤩 The Highlights:

• LlamaAgents Early Access Launch: Deploy document agents with a single click using 90% ready-to-use templates. Automate invoice processing, contract review, and claims handling with managed cloud or bring-your-own infrastructure options. Join Waitlist
• Full-Stack Agent Template with CopilotKit: Build a complete LlamaIndex-powered website in minutes using AG-UI from CopilotKit and Composio. Battle-tested template includes documentation, MCP servers, and troubleshooting guides. GitHub Repository
• Express Agent with TypeScript Workflows: New comprehensive documentation for building production-ready agent systems with tool-calling, state management, human-in-the-loop patterns, and Express server deployment. Documentation

✨ Framework:

• SemTools Benchmark Results: New research comparing coding agents with CLI tools versus semantic search capabilities using 1000 arXiv papers. Shows semantic search provides more comprehensive answers while Unix tooling gives powerful grep, find, and navigation capabilities. Blog Post
• Claude Sonnet 4.5 Day-0 Support: Immediate support for Anthropic's latest model with demo notebook featuring AI-generated fireworks celebration code. Demo Notebook | Get Started

✍️ Community:

• German Snippets Full-Stack Example: OSS engineer Clelia built a complete agent application using LlamaIndex Workflows, Next.js, and Tailwind CSS with Qdrant vector DB and OpenAI translation layer. Live Demo | GitHub Repository | TypeScript Workflows Docs