Xedant Data Agent

Collect data from anywhere — just ask the agent. It writes the scripts, runs them on time, and Analytics Agent turns the results into clear reports

Xedant Data Agent is data collection without programming. You describe in chat what you need (“collect competitor prices once a day”, “pull our order statistics”), and the agent writes and maintains the scripts, runs them on demand or on a schedule, and puts the results into a tidy Lakehouse: raw files, a database for visualization, a description and logs for every source. Then Analytics Agent steps in: it builds reports, charts and dashboards from the collected data. There is no manual data entry and no manual script editing in the Data Agent interface — that is the agent’s job.

When there is a lot to gather — hundreds of pages, dozens of queries, thousands of short texts — harvesters come into play: services for bulk search, page download and text processing by AI models. The agent launches them on its own; you watch the results and the costs.

Collect data from anywhere: APIs, websites, databases — anything a script can pull

Scripts are written and maintained by the agent in chat — no programming needed

Run on demand or on a schedule: from every 15 minutes to once a day

Scripts are plain files in a folder: Git, versioning, copy to move

Live run output with logs and history

Data lands in a Lakehouse: Parquet as the raw source, SQLite for visualization

A README describes every data source: what, where and how it is collected

Bulk collection: hundreds of pages, queries and texts in a single run

Data sources are detected automatically — one per Lakehouse folder

SQLite databases are ready for Analytics Agent visualization right after loading

Built-in scheduler: schedule changes are picked up on the fly

Downtime causes no run storms: the schedule resumes cleanly, with optional catch-up

Agent analytics: tokens, cost and load by hours and days

Pick a model and a skill for every task in chat

Prompts queue: the agent works through tasks one by one

Harvesters for search, download and generation — configured once, applied by the agent

Runs on your central Xedant Agent — no extra keys or subscriptions

The scripts folder is shared with Xedant Agent: both sides see the same files

On your own server: one Docker container, data in the /data volume

SQLite or PostgreSQL — your choice

Complete English interface localization

Mobile interface: keep an eye on runs from your phone

Part of the AI agent ecosystem: Research Agent collects knowledge, Data Agent collects data, Analytics Agent builds reports

Data on request

Chat with the agent: describe in words what data you need

Describe the data you need in words — the agent writes the script and runs it

Scripts are created and fixed in chat — nothing to edit in the interface

Pick a model and a skill for every task

Agent changes are committed to Git — the full edit history is at hand

Scripts: just a plain folder

Scripts are plain files in a folder: folder tree and code viewing

Every data source is a separate folder: scripts, docs and notes

A page for every folder and file with clean formatting

Search across all files as you type

Agent changes appear instantly — no reload needed

One-click runs

Runs: live output and script run history

A Run button on the page of any script

Live output — you see what is happening right now

Run history with results, logs and labels: manual / scheduled / by agent

Stop, timeouts and a shared queue

Scheduling without the hassle

Scheduler: intervals and exact times for script runs

The schedule is a single schedule.yml file — the agent changes it on your request

Intervals (every 15 minutes, once a day) and exact time — down to the second

Changes are picked up on the fly — no reload

Downtime is survivable: the schedule resumes cleanly, with optional catch-up

Lakehouse: data kept in order

Lakehouse: projects and data sources, each in its place

Project → source structure: everything is in its place

Parquet is always the raw data, SQLite is the visualization database

A README describes each source, run logs lie next to the data

Source overview: size, freshness, browsing right from the browser

Data sources

Data sources: automatic discovery and table schemas

Automatic discovery: a database appears in the Lakehouse — the source is ready

Table schemas are visible right away

Overrides and external databases are connected by the agent

Updated after every script run — fresh data right away

Bulk data harvesting

Harvesters: bulk search, page download and text processing by AI models

Bulk search across dozens of queries at once — Google, Brave, DuckDuckGo and other services

Hundreds of pages downloaded: a plain request, a proxy or an invisible browser — bot-protected sites give in too

Text processed by models in bulk: labelling, field extraction, translation

If one service fails, the harvest moves on to the next — the data is collected anyway

You see how many tasks are done, how much was spent and how long is left

Harvest jobs live in the app database — a server restart does not lose them

Data for Analytics Agent

Collected data is ready for visualization in Analytics Agent

Collected data is ready for visualization right after loading

Analytics Agent builds reports, charts and dashboards on it

A clean SQLite database is the result of every pipeline

Data Agent collects, Analytics Agent shows — one pair

Analytics reads data, changes go through the protected Data Agent API

Agent analytics

Agent analytics: tokens, cost and load by day

How many tokens and how much money the data collection costs

Load by hours of the day and days of the week

Distributions of duration and response speed

Cost by models and by chats

Runs on Xedant Agent

Data Agent runs on your central Xedant Agent

Chat and AI features come from your central Xedant Agent

No extra keys or subscriptions

One agent chat on every page of the interface

The agent drives data collection via its API: sessions, runs, schedules

Everything on your server

One Docker container: Data Agent deploys on your server

One Docker container — and everything works

All data lives in the /data volume — it survives container recreation

The scripts folder is shared with Xedant Agent — both sides see the same files

SQLite or PostgreSQL — your choice

The license is activated with a key in the interface. Without a valid license, sending messages to the agent and managing the prompts queue do not work; runs, the scheduler, the Lakehouse and browsing data all work without a license. The data stays yours: scripts are plain files in a folder, data lives in the Lakehouse on your disk.

Personal license

Every Data Agent feature with no limits for individuals: unlimited installations on any of your computers and servers. $197 one-time payment for a lifetime license. 12 months of free updates, then (optionally) a 50% discount on the next 12 months of updates from the original purchase price. Licensing works offline, and your key is truly lifetime. The matching Xedant Agent license is already included — the Agent is part of the product.

Company license

Every Data Agent feature with no limits for everyone in a company or team, external contractors included. $497 one-time payment for a lifetime license with 12 months of free updates, then (optionally) a 50% discount on the next 12 months of updates from the original purchase price. Licensing works offline, and your key is truly lifetime. The matching Xedant Agent license is already included — the Agent is part of the product.

Service license

Unlimited instances of Data Agent under your domain + the full source code with the right to change it any way you like, update the UI or branding for your company or domain, and integrate it closely with your infrastructure. Any visitor of your domain may use it as part of your services. $970 one-time payment for a lifetime license with 12 months of free updates, then (optionally) a 50% discount on the next 12 months of updates from the original purchase price. Licensing works offline, and your key is truly lifetime. The matching Xedant Agent service license is already included — the Agent is part of the product. The Agent’s source code is available only when you buy the service license for Xedant Agent itself. For smooth upgrades, we recommend changing only the branding and the integration — that keeps the effort of merging new features and fixes to a minimum.

Free licenses

In some cases we are happy to gift a free license:

  • if you found a bug or a security vulnerability in any of our products (we honestly have no budget for a paid bug bounty, unfortunately);
  • if you suggested a sound idea for improving our products (no coding needed — a useful idea is enough; you get a license if we add it to the roadmap);
  • if you are an active contributor to open-source projects (we love open-source — we just have no time to maintain our own products as open-source);
  • if you run a popular blog, Telegram channel or YouTube channel about programming, AI, analytics, marketing, business, finance or IT in general (no mention or promotion required — it is entirely up to you);
  • if you are an active affiliate partner (sales are not required, but you should have at least some content dedicated to our products).

If any of the above is about you, just write to us on Telegram. Tell us your name and email, and we will generate your personal lifetime license key.