LlamaIndex Newsletter 2026-01-06：Agent Workflows 集成 ACP、文档 Agent 模板与 LlamaParse 更新

Hi there, Llama Enthusiasts! 🦙

Welcome to 2026! We're kicking off the new year with exciting developments in document AI workflows. This week brings powerful Agent Workflow integrations with the Agent Client Protocol, pre-built document agent templates for instant deployment, and continued improvements to our LlamaParse products. Let's make 2026 the year of production-ready document AI!

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.

📅 First Webinar of 2026:

Join Logan Markewich for our first webinar of the year: Turn Messy Spreadsheets into Structured Parquet Files with LlamaSheets. Learn how to automatically extract structured data from complex Excel files and build agents that analyze financial reports, consolidate multi-region data, and automate weekly reporting—all in a few lines of code. Register here

Explore our free and paid plans today.

🎉 The Highlights:

• Agent Workflows with ACP Integration: Powerful integration with the Agent Client Protocol, creating a fully customizable agent with filesystem and bash tools, MCP servers, persistent memory, and built-in TODO tracking. Get started with LlamaAgents, GitHub repo.
• Pre-built Document Agent Templates: Launch document workflows instantly with our collection of LlamaAgent templates covering everything from simple Q&A to complex invoice processing, complete with UI components and one-command deployment via llamactl. Browse all agent templates.
• Vibe-Coding Document Extraction: New features for creating document extraction engines with intuitive, flexible approaches to handling complex document processing workflows.

☁️ LlamaParse:

• We're listening! LlamaSheets is in beta and we want your feedback: LlamaSheets handles messy spreadsheets—merged cells, broken layouts, headers spanning rows—and outputs clean Parquet files with 40+ cell-level features. Drop feedback in the Cloud UI or fill out this form for an in-depth product feedback session. Get started here.
• LlamaSplit: Automatically separate bundled documents into distinct sections using AI to analyze page content and group consecutive pages by category.