# Alembic: Data Distiller — Clean data for AI and RAG

> Clean data for AI and RAG (iPhone/iPad app by Luke Mclaughlin.)

- Source: https://appshunter.io/ios/app/alembic-data-distiller/id6790155591 (this page in markdown: same URL + `.md`)
- Developer: [Luke Mclaughlin](https://appshunter.io/developer/1893671036)
- Category: Developer Tools, Business
- Price: Free with in-app purchases
- Age rating: 4+
- Requires: iOS 17.0 · 6 MB
- Languages: American English
- Released: 2026-07-24
- Data updated: 2026-08-29
- User reviews in markdown: https://appshunter.io/ios/app/alembic-data-distiller/id6790155591/reviews.md

## What is Alembic?

Alembic is a professional, private data-preparation workspace for turning messy source material into dependable training datasets and retrieval-ready collections.

IMPORT REAL-WORLD DATA
Open CSV, TSV, JSON, JSONL, SQLite, Markdown, HTML, plain text, code, or entire document folders. Alembic detects structure, encoding, delimiters, types, and import problems before processing begins.

DESIGN A REPEATABLE PIPELINE
Compose deterministic steps for normalization, null handling, type inference, exact and near-duplicate removal, quality filtering, token counting, semantic chunking, privacy scrubbing, decontamination, schema shaping, and dataset splitting. Disable, reorder, inspect, and replay every step.

PREPARE TRAINING AND RAG DATA
Shape clean records for Alpaca, OpenAI, Anthropic, ChatML, and DPO structures. Build reproducible splits, sentence-aware token-budgeted chunks, heading paths, metadata, real cl100k token counts, and embedding-ready JSONL.

PRIVACY AND QUALITY CONTROLS
Detect and redact emails, phone numbers, addresses, credentials, API keys, financial identifiers, and other sensitive patterns. Screen against evaluation sets, identify exact and fuzzy duplicates, and inspect quality metrics before export.

LOCAL BY DEFAULT
The deterministic pipeline works locally. Optional provider augmentation uses a provider you configure; credentials stay in Keychain and selected content goes directly to that provider.

FREE AND PRO
Importing, the complete deterministic pipeline, preview, dataset reports, and export are free forever. Alembic Pro is an optional auto-renewable subscription with monthly and annual choices and an eligible 7-day free trial. Pro unlocks LLM-assisted Q&A generation, quality scoring, rewriting, classification, and preference-pair creation. The current localized price and trial eligibility are always supplied by the App Store before purchase. Restore Purchases and Manage Subscription are available in Settings.

Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/
Privacy Policy: https://github.com/lukekevinmclaughlin-oss/Alembic/blob/main/PRIVACY.md

## Pricing and in-app purchases

Base price: Free.

**Subscriptions**

| Subscription | Price | Period |
| --- | --- | --- |
| Alembic Pro Annual | $29.99 | per year |
| Alembic Pro Monthly Plan | $4.99 | per month |



## Version history (last 2 releases)

### 1.1 — 2026-08-22

Alembic 1.1 introduces a genuinely useful free workflow and a clearer, more reliable Pro experience.

• The complete deterministic pipeline, reports, and exports now work without subscribing.
• Choose monthly or annual Pro with accurate StoreKit pricing and trial eligibility.
• Restore purchases and manage subscriptions from Settings.
• Improved verified-entitlement, expiry, cancellation, and transaction-update handling.
• Review prompts appear only after successful pipeline milestones, with long cooldowns.

### 1.0 — 2026-07-24

No release notes.

## More apps by Luke Mclaughlin

- [CodeMonkey: Learn to Code](https://appshunter.io/ios/app/codemonkey-learn-to-code/id6783108217)
- [Sparky Learn Languages](https://appshunter.io/ios/app/sparky-learn-languages/id6783108566)
- [Insightful: Learn Math](https://appshunter.io/ios/app/insightful-learn-math/id6787501553)
- [Pronunciation Master: Speak](https://appshunter.io/ios/app/pronunciation-master-speak/id6787513786)
- [Squiddy Constructing Language](https://appshunter.io/ios/app/squiddy-constructing-language/id6787675602)
- [Spider Notes: Mind Maps](https://appshunter.io/ios/app/spider-notes-mind-maps/id6787766534)

All apps by Luke Mclaughlin: https://appshunter.io/developer/1893671036

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-29.*