DocETL
System for agentic, LLM-powered document processing and ETL pipelines from UC Berkeley.
Updated
✨ Try AgentScout's free AI image generator →Good for: building AI agents, working with documents
Use cases
About DocETL
DocETL is listed in our frameworks category and is aimed at builders. System for agentic, LLM-powered document processing and ETL pipelines from UC Berkeley. Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-10-16.
What is DocETL?
DocETL, from UC Berkeley, helps you process large collections of structured and unstructured data with LLMs. You write each operation in natural language, such as pulling every complaint out of a ticket.
It provides operators like map, reduce and filter, parallelizes work across your data and optimizes the pipeline automatically by swapping models, rewriting prompts and decomposing operations. It has a Python API, YAML and the DocWrangler UI.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: docetl.org.
Who is DocETL for?
Data and research teams running LLM-powered extraction over large document sets.
DocETL at a glance
- Open source: Yes (MIT License)
- GitHub: ucbepic/docetl · 4,137 stars (as of Oct 21, 2026)
Key features
- Natural-language operations
- Map, reduce, filter operators
- Automatic pipeline optimization
- Python API, YAML and DocWrangler UI
DocETL FAQ
What is DocETL?
DocETL, from UC Berkeley, helps you process large collections of structured and unstructured data with LLMs. You write each operation in natural language, such as pulling every complaint out of a ticket.
Who is DocETL for?
Data and research teams running LLM-powered extraction over large document sets.
Is DocETL free?
DocETL's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is DocETL open source?
Yes. DocETL is released under the MIT License, according to its GitHub repository.
What are alternatives to DocETL?
Similar tools include LlamaIndex, OpenFang, Spring AI Alibaba, Prime Intellect, Go Micro and AgentFlow.
DocETL ratings and reviews
Be the first to rate DocETL: tap 1 to 5 stars below. A written review is optional.
DocETL alternatives
Other frameworks tools in our directory. See all frameworks tools →
LlamaIndex
Framework for agents over your data (RAG, document agents).
OpenFang
Open-source agent operating system for running autonomous agents.
Spring AI Alibaba
Agentic AI framework for Java developers built on Spring AI.
Prime Intellect
Decentralized compute and open RL environment hub for training agentic models.
Go Micro
Go framework for distributed systems where services double as tools for AI agents, with RPC, discovery, messaging and agent workflows.
AgentFlow
Stanford's trainable agentic system where planner, executor, verifier and generator modules coordinate, with a Hugging Face demo.
Related lists
🏆 Ranked in: LlamaIndex alternatives · PrivateGPT alternatives
🔁 Listed in: LlamaIndex alternatives · PrivateGPT alternatives
🧭 Task guides: RAG and document tools for building AI agents
💲 Estimate API cost: compare per-request and monthly costs for GPT, Claude, Gemini and Grok models.
Badge for makers
Built DocETL? Add this badge to your README or site. It links back to this page. About badges
