ToolAI Tools & APIsv0.2

DocETL

by UC Berkeley · open-source · Last verified 2026-03-17

LLM-powered ETL system for complex document processing and analysis pipelines from UC Berkeley. Optimizes multi-step document processing workflows with automatic plan generation and quality assessment.

https://ucbepic.github.io/docetl/ ↗

D—Poor

Adoption: DQuality: B+Freshness: ACitations: DEngagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: document-etl, pipeline-optimization, quality-assessment, multi-step-processing, llm-operations
Integrations: openai, anthropic
Use Cases: document-analysis, data-extraction, research-pipelines, content-processing
API Available: Yes
SDK Languages: python
Deployment: self-hosted
Rate Limits: N/A (open-source)
Data Privacy: Self-hosted, user-managed
Tags: document-processing, etl, llm-powered, data-pipeline
Added: 2026-03-17
Completeness: 100%

Index Score

39.1

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service