01
Databases, files, and MCP
Work across SQLite, PostgreSQL, a bounded local workspace, and explicitly admitted remote read tools.
Your data hasa new interface.
A persistent data agent that investigates, packages, and repeats trusted work. An intelligent pipeline that turns raw files into production-ready data.
Terminal agent
The agent lives where your work already happens.
Launch Daita and work across live databases, local files, and admitted remote tools. It grounds each answer in inspectable evidence, creates useful deliverables, and carries bounded work forward.
Persistent context + outcomesRead first / human controlled
02
Read first. Change by approval.
Keep analysis read-first, then opt into exact file replacements or scoped PostgreSQL updates when needed.
03
Outcomes that persist
Create reports and exports, run durable data profiles, and repeat bounded read work on a schedule.
Two commands. Your first question.
$ curl -fsSL https://daita-tech.io/install.sh | bash$ daitaAgentic pipeline
In development / coming to WebUIFrom raw file to live schema, with judgment at every step.
Upload a file, select a destination, and watch the pipeline map, validate, transform, resolve, and load your data—asking for context only when it needs you.
SourceMeaningDestination
Rows18,420
Mappings24 / 24
Confidence94.2%
✓
Source profiled18,420 records · 24 columns · 3 sheets
✓
Schema mapping accepted24 mappings cleared the 60% confidence threshold
✓
Validation completeTypes, nullability, uniqueness, and checks verified
Resolving account relationshipsMatching portfolio.owner_ref → accounts.external_id
Pipeline needs your context
Two records match “North Star Holdings.” Which account owns this portfolio?
Pipeline resumes after your answer.Map
Match source fields to the live destination schema.
Validate
Check types, constraints, required values, and relationships.
Clarify
Ask for human judgment when meaning is ambiguous.
Transform
Generate and apply the required cleanup recipes.
Resolve
Connect foreign keys and preserve parent-child records.
Generate
Build correlated SQL only after confidence clears the threshold.
Load
Execute with a live, inspectable progress stream in the WebUI.
Understand the data you have.Build the data you need.
01
Ask
The terminal agent turns your existing data into a persistent, grounded conversation.
Explore the agent02
Move
The pipeline turns incoming data into validated, connected records inside your destination schema.
Explore the pipelineOpen source and designed for people who work with data.