Skip to main content

convoviz

Turn your ChatGPT export into Markdown notes and charts.
Read and search your whole chat history in Obsidian or any Markdown app. Runs on your computer.

PyPI version Python 3.12+ Downloads Tests Made for Obsidian

The insights page convoviz creates: totals for conversations, prompts and active days, and a heatmap of when in the week the prompts were sent
Made from an invented export. Yours never leaves your computer.

Quick start

1. In ChatGPT, open Settings → Data controls → Export data, and download the ZIP from the email.

2. Install convoviz:

# macOS / Linux
curl -LsSf https://raw.githubusercontent.com/mohamed-chs/convoviz/main/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/mohamed-chs/convoviz/main/install.ps1 | iex"

3. Run it:

convoviz

It finds the newest export in Downloads and writes your archive to Documents/ChatGPT Archive.

New to the terminal?

Open Terminal (macOS: ⌘ Space, type Terminal) or PowerShell (Windows: press Windows, type PowerShell). Paste the install line, press Enter, then open a new window and type convoviz.

The installer sets up uv, which handles Python for you. Already have uv? Run uv tool install convoviz.

What you get

Your exportYour archive
"n1": {
  "parent": "root",
  "message": {
    "author": {"role": "user"},
    "create_time": 1773480612.0,
    "content": {
      "content_type": "text",
      "parts": [
        "Three days in Kyoto in…"
      ]
    }
  }
},
"n2": {
  "parent": "n1",
  "message": {
    "author": {"role": "assistant"},
    "content": {
      "content_type": "thoughts",
      // … and on, for every message
---
created: 2026-03-14T09:30:12
models: ["gpt-5-5-thinking"]
tags: ["chatgpt"]
---

# Planning a trip to Kyoto

## You · 2026-03-14 09:30

Three days in Kyoto in April —
what should I not miss?

## ChatGPT · 2026-03-14 09:30

<details>
<summary>Thought for 8s</summary>…

- **Fushimi Inari** early, before
  the tour groups[^1].
…
  • One Markdown note per conversation, sorted by year. See a full example.
  • Sources as footnotes, reasoning and tool output folded, edited replies kept.
  • Images, files and Canvas documents saved next to the notes.
  • An index, and a sortable table of every conversation in Obsidian.
  • insights.html: charts and word clouds of how you use ChatGPT, offline.

A word cloud of the topics asked about, with tabs for each year

More charts

A calendar of prompts per day for each year, and a stacked chart of replies per month by model

Updating

Run it again on a newer export. Only new and changed conversations are written. Notes you edited, moved or deleted stay as you left them (--force overrides that).

Options

convoviz ~/Downloads/chatgpt-export.zip -o ~/Notes/ChatGPT
Flag
-o PATH Output folder
--layout flat All notes in one folder, not one per year
--branches active Only the replies you last viewed
--timezone Europe/Paris Time zone for dates
--no-insights Skip the charts
-y Don't ask before using the export found in Downloads

convoviz config init creates a settings file for labels, tags, words to leave out of word clouds, and more.

FAQ

Is my data uploaded anywhere?

No. convoviz makes no network requests, and the charts page loads nothing from the internet.

Do I need Obsidian?

No. The notes are standard Markdown and open in VS Code, on GitHub, or in any Markdown app. Only Conversations.base is Obsidian-specific.

Which exports does it read?

ChatGPT's 2026 format: the ZIP, an extracted folder, or conversations.json, including split and multi-part exports. Business and Enterprise workspaces can't export.

Can I make PDFs?

Yes, with convpdf: convpdf "conversations/**/*.md" -o PDF/.

I used convoviz 0.x.

1.0 writes to a new folder and leaves the old one alone. Run convoviz config init --force to update an old config file.

Something wrong?

Run convoviz inspect --json and paste the output into a bug report. It lists the export's structure only, never your conversations.

If convoviz helped you, a ⭐ helps others find it. To contribute, see CONTRIBUTING.md. MIT license.

Metadata

Release files for convoviz 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for convoviz 1.0.1
File Size Uploaded Provenance Actions
convoviz-1.0.1.tar.gz 75.1 kB With provenance Details for convoviz-1.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for convoviz 1.0.1
File Interpreter ABI Platform Actions
convoviz-1.0.1-py3-none-any.whl Python 3 none any Details for convoviz-1.0.1-py3-none-any.whl

Total release size: 158.2 kB

Release files / convoviz-1.0.1.tar.gz

Download URL convoviz-1.0.1.tar.gz
Size 75.1 kB
Tags Source
SHA-256 checksum
How to use checksums
639fb150ddf97e9225f9e389e22382a1422258ba91358a9053693d409c0627a6
BLAKE2b-256 checksum
How to use checksums
0f652d46e9d11e1dbafcd14b6e8bd550d0c0e16072f0203d6b4efda9bd3ea4ae
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 4, 2026.

Transparency log

Release files / convoviz-1.0.1-py3-none-any.whl

Download URL convoviz-1.0.1-py3-none-any.whl
Size 83.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b62bddc55ad4453731e1ac90b7d0ac1ae6f24803d718bef102bf8e3240ddf888
BLAKE2b-256 checksum
How to use checksums
5399f4332f6831853c30d94aeb507dad350bb1e5093652d6cbbfa88f9eb35830
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 4, 2026.

Transparency log

Security for convoviz 1.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for convoviz-1.0.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 4, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page