datarep 1.0.0

A user-authorized agent runtime that acquires data from arbitrary sources and delivers it to consuming applications.

datarep

A trusted local service that retrieves data from arbitrary sources on behalf of your application. Your app describes what data it wants — datarep figures out how to get it.

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"}'

What it does

Instead of every app building its own integrations, datarep:

• Manages credentials — encrypted storage, browser-based OAuth, automatic token refresh
• Writes retrieval code — a Claude agent inspects sources and generates Python code dynamically
• Executes in a sandbox — network and filesystem restrictions via macOS sandbox-exec
• Caches as recipes — working code is saved for instant, deterministic replay
• Authenticates apps — per-app API keys with source-level access control and audit logging

Users grant trust once (to datarep). 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