P
pwallace/mnemotron-wiki
Mnemotron Wiki is a Claude-powered system that synthesizes professional documents, email, calendar data, and…
updated 2026-11-16
View on GitHub ↗Link checked 2026-11-17 · HTTP 200 · opens the vendor's own site
- Star count
- 0 ★ · pwallace/mnemotron-wiki · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-17 · last seen 2026-11-20 · seen 4× · listed by 1 sources
- Score
- score 103 · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Open Source. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
pwallace/mnemotron-wiki;first catalogued 2026-11-17;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# Mnemotron Wiki
Excerpted from the repository README (abridged)
> Created with assistance from Claude Code (Claude Sonnet 5.5); may not have been fully reviewed by a human.
A personal knowledge base that builds itself from your work.
Copyright (C) 2026 Patrick R. Wallace, Hamilton College LITS
Code and Claude instruction documents (_TASK.md): GPL-3.0-or-later | Documentation: GFDL-1.3-or-later | See License
> AI-assisted software notice: This software was created with assistance
> from Claude Code (Claude Sonnet 5.5). It may not have been fully reviewed by
> a human. Test it in your own environment before relying on it; you are
> responsible for validating its behavior and for what you send to any AI
> service.
Mnemotron Wiki is a Claude-powered system that synthesizes professional
documents, email, calendar data, and project notes into a structured,
searchable Markdown wiki. You supply the raw material; Claude distills it
into dossiers, topic pages, converted-document pages, and a running index. Everything lives in plain
Markdown files that you own, version with git, and read in any editor.
## Contents
How it works
Privacy and data handling ← read before setup
Requirements
Claude backends
Concurrency and parallel agents
Quick start
Detailed setup
Usage guide
Optional connectors
Organization-specific connectors
Email archive (verbatim)
Exporting a static site
Utility scripts reference
Customizing the pipeline
Scheduling automated runs
Directory reference
Relationship to the sibling tool
License
Credits
## How it works
The system has three layers.
1. Drop zone (raw_ingest/)
Drop any supported document here: PDFs (including scans, via OCR), Word
files, meeting notes, email exports. Optional connector tasks (Gmail, Google
Calendar, Asana, daily briefings) can also write here before a wiki update
runs.
2. The wiki update task
Say "run the wiki update task" in a Claude session. Claude reads
WIKI_UPDATE_TASK.md, scans raw_ingest/ for new files, synthesizes each
document into wiki pages, updates the main index, and commits to git. A
content-hash manifest ensures nothing is processed twice.
3. The wiki (wiki/)
Plain Markdown files in six directories:
| Directory | Contents |
| wiki/daily/ | Dated journal entries (from briefings or Asana summaries) |
| wiki/topics/ | One page per project, initiative, or concept |
| wiki/people/ | One dossier per person |
| wiki/organizations/ | One page per org, team, or department |
| wiki/documents/ | Converted PDF / Word / HTML documents, each with a short generated summary header and links to related pages |
| wiki/email/ | Verbatim archived email — a separate, on-demand task; see Email archive (verbatim) |
A typical run looks like this:
$ cd /path/to/my-wiki
$ claude
> Run the wiki update task.
[Claude scans raw_ingest/, processes 3 new files, updates 2 topic pages,
creates 1 new people page, regenerates INDEX.md, and commits.]
Wiki update complete — 2026-04-24
Files processed: 3
Pages updated: 2
Pages created: 1
Commit: wiki update 2026-04-24
## Privacy and data handling
Read this section before setting up the system.
### What stays on your machine
Your wiki files are plain Markdown stored locally in a git repository. They
do not leave your machine unless you push to a remote git repository or send
A personal knowledge base that builds itself from your work.
Copyright (C) 2026 Patrick R. Wallace, Hamilton College LITS
Code and Claude instruction documents (_TASK.md): GPL-3.0-or-later | Documentation: GFDL-1.3-or-later | See License
> AI-assisted software notice: This software was created with assistance
> from Claude Code (Claude Sonnet 5.5). It may not have been fully reviewed by
> a human. Test it in your own environment before relying on it; you are
> responsible for validating its behavior and for what you send to any AI
> service.
Mnemotron Wiki is a Claude-powered system that synthesizes professional
documents, email, calendar data, and project notes into a structured,
searchable Markdown wiki. You supply the raw material; Claude distills it
into dossiers, topic pages, converted-document pages, and a running index. Everything lives in plain
Markdown files that you own, version with git, and read in any editor.
## Contents
How it works
Privacy and data handling ← read before setup
Requirements
Claude backends
Concurrency and parallel agents
Quick start
Detailed setup
Usage guide
Optional connectors
Organization-specific connectors
Email archive (verbatim)
Exporting a static site
Utility scripts reference
Customizing the pipeline
Scheduling automated runs
Directory reference
Relationship to the sibling tool
License
Credits
## How it works
The system has three layers.
1. Drop zone (raw_ingest/)
Drop any supported document here: PDFs (including scans, via OCR), Word
files, meeting notes, email exports. Optional connector tasks (Gmail, Google
Calendar, Asana, daily briefings) can also write here before a wiki update
runs.
2. The wiki update task
Say "run the wiki update task" in a Claude session. Claude reads
WIKI_UPDATE_TASK.md, scans raw_ingest/ for new files, synthesizes each
document into wiki pages, updates the main index, and commits to git. A
content-hash manifest ensures nothing is processed twice.
3. The wiki (wiki/)
Plain Markdown files in six directories:
| Directory | Contents |
| wiki/daily/ | Dated journal entries (from briefings or Asana summaries) |
| wiki/topics/ | One page per project, initiative, or concept |
| wiki/people/ | One dossier per person |
| wiki/organizations/ | One page per org, team, or department |
| wiki/documents/ | Converted PDF / Word / HTML documents, each with a short generated summary header and links to related pages |
| wiki/email/ | Verbatim archived email — a separate, on-demand task; see Email archive (verbatim) |
A typical run looks like this:
$ cd /path/to/my-wiki
$ claude
> Run the wiki update task.
[Claude scans raw_ingest/, processes 3 new files, updates 2 topic pages,
creates 1 new people page, regenerates INDEX.md, and commits.]
Wiki update complete — 2026-04-24
Files processed: 3
Pages updated: 2
Pages created: 1
Commit: wiki update 2026-04-24
## Privacy and data handling
Read this section before setting up the system.
### What stays on your machine
Your wiki files are plain Markdown stored locally in a git repository. They
do not leave your machine unless you push to a remote git repository or send
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/pwallace-mnemotron-wiki/)
- Source
- github · https://github.com/pwallace/mnemotron-wiki
- Browse by field
- Open source
- added
- today
More entries
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.