Open-source AI data analysis canvas. Connect CSV, JSON, or a live URL, describe a chart in plain English, and get an editable artifact — not a code dump.
DataLane is the open-source, self-hosted answer to AI data-analysis tools that only hand you generated scripts. It runs entirely on your machine, works with your own model key, and every chart is a real object you can edit, branch, and re-render.
- You have data scattered across files and URLs and want charts without writing SQL or Python by hand.
- AI analysis tools give you a script you must re-run; DataLane hands you an editable HTML artifact with the spec + data embedded.
- Follow-up questions drift back to raw data; DataLane anchors a cleaned state so each question builds on the last.
npm install -g @talocode/datalane
# or
pip install talocode-datalanedatalane analyze sales.csv "total revenue by month" --out revenue.htmlfrom talocode import DataLaneClient
client = DataLaneClient()
source = client.load("sales.csv")
result = client.analyze(source, "average revenue by region")
print(result.summary)
client.to_html(result) # editable artifactdatalane analyze <source> "<intent>" [--out <file.html>]
datalane render <source> --spec '<json>' [--out <file.html>]
datalane anchor <source> [--name <name>]
datalane from-anchor "<intent>" [--out <file.html>]
datalane branch --spec '<json>' --vars '<json>' [--out-dir <dir>]
datalane columns <source>
datalane sources | pricing | capabilities
bar, line, scatter, pie, table
sum, avg, count, min, max
| Source | Example |
|---|---|
| CSV file | sales.csv |
| JSON file | data.json (array or { "rows": [...] }) |
| Live URL | https://api.example.com/data.json |
Plain-English phrases are parsed deterministically — no key required:
"total revenue by month"→ bar, sum of revenue grouped by month"average spend by country limit 5"→ avg, filtered to 5 rows"how many orders by region"→ count"revenue trend over time"→ line chart"breakdown by region as a pie"→ pie"correlation between x and y"→ scatter"where region contains South"→ filter
anchor saves the cleaned dataset to .datalane/anchor.json. from-anchor
and branch build on that clean state so follow-ups do not drift back to raw
data.
DataLane ships an MCP server (model context protocol) so any MCP-capable agent can load data, analyze it, render charts, and branch clean state:
{
"mcpServers": {
"datalane": {
"command": "npx",
"args": ["-y", "@talocode/datalane", "--mcp"]
}
}
}Tools: datalane_load, datalane_analyze, datalane_render,
datalane_anchor, datalane_from_anchor, datalane_branch,
datalane_pricing, datalane_capabilities. The MCP server runs locally and
never sends your data anywhere.
import { DataLaneClient } from '@talocode/datalane'
const client = new DataLaneClient()
const source = await client.load('sales.csv')
const result = client.analyze(source, 'total revenue by month')
console.log(result.summary)from talocode_datalane import DataLaneClient
client = DataLaneClient()
source = client.load("sales.csv")
result = client.analyze(source, "average revenue by region")
print(result.summary)
client.to_html(result) # editable artifact| Route | Credits |
|---|---|
datalane.analyze |
5 |
datalane.anchor |
2 |
datalane.render |
1 |
Hosted at https://api.talocode.site/v1/datalane/*. Set TALOCODE_API_KEY
and optionally TALOCODE_BASE_URL.
npm i @talocode/llmgateway/pip install talocode-llmgateway— LLM API gatewaynpm i @talocode/xsearchlane/pip install talocode-xsearchlane— X searchnpm i @talocode/doculane/pip install talocode-doculane— office documents
| Package | GitHub | Install |
|---|---|---|
| DataLane (this package) | talocode/datalane | pip install talocode-datalane |
| Tera | talocode/tera | pip install talocode-tera |
| Codra | talocode/codra | pip install talocode-codra |
| SearchLane | talocode/searchlane | pip install talocode-searchlane |
| StackLane | talocode/stacklane | pip install talocode |
| GateLane | talocode/gatelane | |
| ContextLane | talocode/contextlane | pip install contextlane |
| ScreenLane | talocode/screenlane | pip install talocode-screenlane |
| MemoryLane | talocode/memorylane | |
| Tradia | talocode/tradia | pip install tradia |
| DevTool | talocode/devtool | pip install talocode-devtool |
| XProLane | talocode/xprolane | pip install talocode-xprolane |
| XSearchLane | talocode/xsearchlane | npm i @talocode/xsearchlane |
| Agent Browser | talocode/agent-browser | |
| InvoiceLane | talocode/invoicelane | |
| GeoLane | talocode/geolane | |
| ClipLoop | talocode/cliploop | |
| LLM Gateway | talocode/llmgateway | pip install talocode-llmgateway |
More: github.com/talocode · talocode.site · docs.talocode.site
MIT © Talocode