LlamaIndex Releases LiteParse Agent Skill for Local Document Parsing

LlamaIndex 🦙

Mar 21, 2026 · Updated Apr 25, 2026

LlamaIndex open-sourced LiteParse with a ready-to-use agent skill that lets coding agents parse PDFs and documents locally. Agents can extract text, generate screenshots, and process files as part of their reasoning loop — all without cloud APIs.

LiteParse, an open-source local document parser from LlamaIndex, now ships as a coding agent skill compatible with Claude Code, Cursor, and other coding agents. The skill — installed via Vercel's skills utility from the llamaparse-agent-skills package — gives agents the ability to parse PDFs, extract text from DOCX files, screenshot document pages, and process local files within their reasoning process.

This puts document parsing directly inside the agent loop. Instead of routing files through external services, an agent can read a PDF, pull out text as JSON, screenshot specific pages at custom DPI, or run OCR on scanned documents — all running locally on the developer's machine.

Point your coding agent at a document-heavy task and LiteParse handles it inline. Configure defaults in liteparse.config.json for OCR language, output format, and DPI so the agent skips repetitive setup on every run.

View the full update on developers.llamaindex.ai

LlamaIndex 🦙

@llama_indexMar 20

Our new open-source LiteParse comes with ready-to-use agent skills that work seamlessly with coding agents. `npx skills add run-llama/llamaparse-agent-skills --skill liteparse` ..and your agents can immediately start processing documents locally as part of their reasoning process. Here's Claude Code with liteparse enabled 💪 Documentation for LiteParse agent skills: https://t.co/VEf0zkT9wS

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Keep reading

Weaviate Adds PDF Support to Agent Skills for Autonomous Document Ingestion

Weaviate added PDF import capabilities to its Agent Skills framework, allowing AI agents to autonomously configure schemas and ingest document libraries. By combining multimodal embeddings with the MUVERA algorithm, the system enables high-accuracy multi-vector retrieval without the typical memory and cost overhead.

Elastic DevMar 18

Elastic Open-Sources Agent Skills to Give Coding Agents Platform Expertise

Elastic released Agent Skills, open-source instruction packages that give AI coding agents curated expertise for Elasticsearch, Kibana, Observability, and Security. Skills load into any runtime — Cursor, Claude Code, Copilot — replacing guessed syntax with correct, version-aware operations.

LangChain LangSmith Fleet Shares Agent Skills Across Teams, Keeps Them Synced

LangChainJun 7

LangChain LangSmith Fleet Shares Agent Skills Across Teams, Keeps Them Synced

LangChain has updated its LangSmith Fleet platform to support shareable skills for AI agents. This allows domain experts to codify specialized knowledge once, ensuring consistent, up-to-date information is accessible and usable by all agents across a team without manual coordination. The update helps prevent knowledge silos and accelerates agent development by centralizing expertise.

MiniMax Open-Sources Skills Kit for AI Coding Agents

MiniMaxMar 23

MiniMax Open-Sources Skills Kit for AI Coding Agents

MiniMax released an open-source skills repository for AI coding agents under MIT license. The collection includes curated skills for iOS and Android development, document file editing, and GLSL shaders that plug into compatible coding tools for structured, production-quality guidance.