datarep 1.1.2

Your app's data rep — a local agent runtime that retrieves data from any source on behalf of consuming applications.

datarep

Your app's data rep.

A rep is someone you send to go get something on your behalf. You don't tell them how — you tell them what you need, and they figure it out. They show up, assess the situation, adapt to whatever they find, and come back with the goods.

That's what datarep does. Your app says "get me the user's recent iMessages" and datarep handles it — explores the database schema, identifies the data formats, picks the right parsing libraries, writes the extraction code, tests it, and delivers the data. No one wrote an iMessage integration. The rep wrote one at runtime.

And like a good rep, it learns. Working code is saved as recipes so next time it doesn't have to figure it out again. First request takes seconds. Every request after that is instant.

Why this exists

Every app that needs user data today has to build and maintain its own integrations — or depend on a cloud service that proxies the user's data through someone else's servers. datarep is a different approach: a local agent runtime that synthesizes integrations on demand, runs on the user's machine, and never sends their data anywhere.

There isn't really a category for this yet. It's not a connector (those are pre-built by humans), not an ETL pipeline, not an SDK. It's an autonomous agent that becomes a connector — for any source, on the fly.

Quick start

pip install -e ".[dev]"
datarep init
export ANTHROPIC_API_KEY="sk-ant-..."
datarep start

Register your app and get an API key:

datarep app register my-app

Retrieve data:

curl -X POST http://127.0.0.1:7080/get \
  -H "Authorization: Bearer dr_<your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{"source": "my_source", "query": "get recent records"}'

How it works

Your app tells datarep what data it needs. datarep's agent:

1. Explores the source — inspects schemas, samples data, identifies formats
2. Writes retrieval code — picks the right parsing libraries, handles edge cases
3. Executes in a sandbox — network and filesystem restrictions via macOS sandbox-exec
4. Validates the output — verifies data quality and method correctness before delivering
5. Saves a recipe — working code is cached for instant, deterministic replay

Credentials are encrypted at rest. Apps authenticate with per-app API keys. Users grant trust once (to datarep) and every consuming app gets safe data access through it.

Interfaces

Interface	Use case
HTTP API (localhost:7080)	Primary interface for all apps. Bearer token auth.
MCP server	Native interface for agentic/LLM-powered apps.
CLI (datarep)	Setup, source management, debugging.

Source types

Type	Example	Sandbox
local_db	iMessage chat.db, WhatsApp, any SQLite	No network. Read-only DB access.
rest_api	Square, Gmail, Quickbooks	Network restricted to source domain.
local_files	Photos, documents, exports	No network. Read-only directory access.

Integration guide

See docs/integration-guide.md for the full walkthrough: API reference, authentication, handling permissions, MCP setup, recipes, and code examples.

Development

pip install -e ".[dev]"
pytest