ChatGPT Download Engine

Python CLI · pip package · TypeScript engine

The project in plain English

Why it matters

For People who use AI conversations as working material

The problem

Useful research and working context can become difficult to find when it remains scattered across chat threads.

My contribution

An export pipeline downloads conversations and files, creates readable Markdown, validates links, and installs the archive after staging it.

The value

Makes AI-assisted work easier to retain, inspect, and reuse outside the original chat interface.

ChatGPT Download Engine archive workflow

Skills demonstrated

Data pipelines
Reliability
Developer tooling

Scope & limits. A technical tool that requires setup and access to the user's own account. Availability depends on upstream endpoints. An archive may contain sensitive material and remains the owner's responsibility.

A desktop experience built on this work

The Omarchy ChatGPT Archive brings this archive workflow into a desktop panel with project filters, progress, search, and scheduled exports.

Explore the Omarchy plugin →

Download every
ChatGPT chat. Locally.

A private JSON + Markdown archive of your conversations — citations, timestamps, images, attachments. One command.

$npm install air-cde-runtime

View the package ↗

Python 3.9+Node 20ProprietaryNo servers

zsh

# verify, then archive

$ chatgpt-download-engine doctor

config · token · paths · engine

$ chatgpt-download-engine export incremental

json 128 · md 129 · files 46

installed atomically

0.15s

100 chats → Markdown

messages / run

dependencies

tests passing

OS supported

Diagrams

flowchart LR
    subgraph Python["Python: src/chatgpt_download_engine"]
        CLI2["cli.py"]
        Config2["config.py"]
        Pipeline2["pipeline.py"]
        Markdown2["markdown.py"]
        Validation2["validation.py"]
    end
    subgraph Engine["TypeScript engine"]
        EngineSrc["src/"]
        EngineDist["dist/index.cjs"]
    end
    CLI2 --> Config2 --> Pipeline2
    Pipeline2 --> EngineDist
    EngineSrc --> EngineDist
    Pipeline2 --> Markdown2 --> Validation2

Source modules and the two runtimes.

01config02doctor03stage04engine05download06normalize07markdown08validate09install atomically

Key facts

Platform

Cross-platform

Windows · macOS · Linux

Stack

Two runtimes

Python 3.9+ · Node 20

CLI

Three commands

doctor · export · validate

Output

Portable archive

JSON · Markdown · files

Privacy

Local-only

Tokens, config, exports git-ignored. Secrets redacted from logs.

Safety

Atomic & validated

Staged, validated, swapped in one transaction. Rolls back on failure.

Benchmark offline · reproducible

Local JSON→Markdown render, best of 5, 40 turns each. ~674–980 conv/s. Network excluded. Reproduce: python3 scripts/benchmark.py