Everyrow
Description
 # everyrow SDK [](https://pypi.org/project/everyrow/) [ # everyrow SDK [](https://pypi.org/project/everyrow/) [](#claude-code)…
Details
- Author
- futuresearch
- Downloads
- 121
- Categories
- Other
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
EveryrowCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"everyrow": {
"everyrow": {
"command": "uvx",
"args": [
"everyrow-mcp"
],
"env": {
"EVERYROW_API_KEY": "${EVERYROW_API_KEY}"
}
}
}
}
}McpServers
{
"everyrow": {
"command": "uvx",
"args": [
"everyrow-mcp"
],
"env": {
"EVERYROW_API_KEY": "${EVERYROW_API_KEY}"
}
}
}everyrow SDK
Run LLM research agents at scale. Use them to intelligently sort, filter, merge, dedupe, or add columns to pandas dataframes. Scales to tens of thousands of LLM agents on tens of thousands of rows, all from a single python method. See the docs site.
pip install everyrow
The best experience is inside Claude Code.
claude plugin marketplace add futuresearch/everyrow-sdk
claude plugin install everyrow@futuresearch
Get an API key at everyrow.io/api-key ($20 free credit), then:
import asyncio
import pandas as pd
from everyrow.ops import screen
from pydantic import BaseModel, Field
companies = pd.DataFrame([
{"company": "Airtable",}, {"company": "Vercel",}, {"company": "Notion",}
])
class JobScreenResult(BaseModel):
qualifies: bool = Field(description="True if company lists jobs with all criteria")
async def main():
result = await screen(
task="""Qualifies if: 1. Remote-friendly, 2. Senior, and 3. Discloses salary""",
input=companies,
response_model=JobScreenResult,
)
print(result.data.head())
asyncio.run(main())
Operations
Intelligent data processing can handle tens of thousands of LLM calls, or thousands of LLM web research agents, in each single operation.
| Operation | Intelligence | Scales To |
|---|---|---|
| Screen | Filter by criteria that need judgment | 10k rows |
| Rank | Score rows from research | 10k rows |
| Dedupe | Deduplicate when fuzzy matching fails | 20k rows |
| Merge | Join tables when keys don't match | 5k rows |
| Research | Web research on every row | 10k rows |
See the full API reference, guides, and notebooks, (for example, see our notebook running a Research task on 10k rows, running agents that used 120k LLM calls.)
---
Web Agents
The most basic utility to build from is agent_map, to have LLM web research agents work on every row of the dataframe. Agents are tuned on Deep Research Bench, our benchmark for questions that need extensive searching and cross-referencing, and tuned to get correct answers at minimal cost.
```python
from everyrow.ops import single_agent, agent_map
from pandas import DataFrame
from pydantic import BaseModel
class CompanyInput(BaseModel):
company: str
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
