Everyrow

What is Everyrow?

Everyrow is an SDK to run LLM research agents at scale on pandas dataframes, enabling intelligent sorting, filtering, merging, deduplication, and column addition. It scales to tens of thousands of LLM calls or web research agents from a single Python method.

How to use Everyrow?

Install via pip install everyrow, get an API key at everyrow.io/api-key, then use Python with pandas and Pydantic models to run operations like screen, rank, or research. Integrate with Claude Code, Gemini CLI, Codex CLI, or Cursor via plugins.

Key features of Everyrow

• Screen rows by criteria that need judgment (10k rows)
• Rank and score rows from research (10k rows)
• Deduplicate where fuzzy matching fails (20k rows)
• Merge tables when keys don't match (5k rows)
• Web research agents on every row (10k rows)
• Async operations with crash recovery via fetch_task_data

Use cases of Everyrow

• Filter job listings for remote-friendly senior roles with salary disclosure
• Deduplicate messy CRM exports where exact matching fails
• Merge two tables without clean join keys
• Research company funding rounds and lead investors at scale
• Classify and label thousands of dataframe rows using LLM judgment

FAQ from Everyrow

What Python version is required?

Python 3.12 or newer is required to install and run Everyrow.

How do I get an API key?

Go to everyrow.io/api-key to obtain an API key; you receive $20 in free credit.

Can Everyrow perform web research?

Yes, use single_agent for one row or agent_map for parallel web research agents on every row, tuned for deep research and cost efficiency.

What if my script crashes during an async operation?

Print the task ID after submitting, then use fetch_task_data with that ID to recover the results later.

Which coding agent plugins are supported?

Plugins are available for Claude Code, Gemini CLI, Codex CLI, and Cursor, each with installation steps in the README.