Skip to main content
Glama

Claudette

An assistant that answers only from texts written by women — and says so when they did not write about it.

Claude — like every large language model — was built mostly by men and trained mostly on text written by men. Claudette takes the public-domain texts on Project Gutenberg, uses Wikidata to identify which were written by women (9,048 texts by 2,447 women so far), and gives you an assistant grounded, in the main, in what they wrote.

It is not perfect. It makes no judgement about anyone. It is meant to be interesting, and to redress the balance somewhat.

Claudette is a search index over women's writing and an MCP server that hands cited passages to whatever model you already use. Every answer is built from those passages and cites them so you can check. If the women in the corpus did not write about something, Claudette tells you that, rather than filling the gap from elsewhere.

It comes in two tiers:

  • Core — 36 works by 27 women, 1694–1922, each chosen, checked and annotated by a person. Installs in seconds.

  • Full — every Project Gutenberg text whose every author, editor and translator Wikidata records as a woman: 9,048 texts by 2,447 women, in 18 languages. Built on your machine with one command, in about an hour.

MIT licensed. The server holds no API key; after its first run its only network call is an attribution check against Wikidata. It runs on your Claude subscription, not the author's.


Why

Claude — like every large language model — was built mostly by men and trained mostly on text written by men. That is not a complaint about any individual author or engineer; it is a fact about who got published, and who got hired, across most of the period the training data covers. Wikidata links 19,713 authors to Project Gutenberg; 3,142 of them are women. Sixteen percent. And it has a flavour. The management canon in particular — from Taylor's stopwatch onward — is a literature of control: how to get more out of people who are treated as inputs.

There was always another literature. Mary Parker Follett was writing about power-with rather than power-over in 1918, while scientific management was at its height; her work was buried for fifty years and is now quietly cited by everyone who writes about collaboration. Jane Addams ran an institution on the principle that you cannot judge someone's conduct until you have understood their situation. Elizabeth Gaskell wrote the industrial novel from inside a strike and gave both sides faces. Ida Tarbell documented, from the primary sources, what a very rich man does when nobody stops him.

Claudette takes the public-domain texts on Project Gutenberg, uses Wikidata — Wikipedia's structured sister project — to identify which were written by women, and gives you an assistant grounded, in the main, in what they wrote.

It is not perfect. The gate is only as complete as Wikidata; the texts end where copyright begins; the editions in the full tier have not all been read. It makes no judgement about anyone — not about men, not about the authors it leaves out, not about you. It is meant to be interesting, and to redress the balance somewhat. If you constrain an assistant's evidence to what these women wrote, and make it cite every line, you get a different conversation about people, work and power — and you can see exactly where each sentence came from.

Related MCP server: farr-cite

What it is not

It is not a language model trained only on women's writing. Nobody can build that in an afternoon and anyone who says they have is selling something. Claudette's evidence is constrained; the prose is generated by a general model (Claude, by default). The guarantee is about where what she tells you came from, not about the training data of the model that phrases it — and it has two strengths, which every answer distinguishes: provable for what she quotes from the corpus, attributed and checkable for what she draws from memory about women thinkers since (see Lens mode below). The corpus_provenance tool says this too, in every session.


The server speaks MCP over stdio. Add it to Claude Code:

claude mcp add claudette -- uvx --from git+https://github.com/michaelcpattinson-star/claudette claudette-mcp

Or to Claude Desktop, in claude_desktop_config.json:

{
  "mcpServers": {
    "claudette": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/michaelcpattinson-star/claudette", "claudette-mcp"]
    }
  }
}

Using her in the Claude desktop app's chat tab

The chat tab has no CLAUDE.md, so load her one of two ways.

A Claudette Project (recommended — set up once, then just talk). A Project's custom instructions apply to every conversation inside it, which is the same lever CLAUDE.md gives Claude Code.

  1. Projects (left sidebar) → Create project → name it Claudette.

  2. Open the project's Instructions and paste the contents of PROJECT_INSTRUCTIONS.md — her full persona and all of her convictions, about 30k characters, which fits.

  3. In any chat in that project, click the sliders / "Search and tools" icon by the message box and check the claudette connector is on. (Not listed? Quit and reopen the app; it reads its config at launch.)

  4. Ask her anything. No "ask Claudette" needed — she is the project.

Per conversation, from the connector's prompt. The connector publishes a prompt named claudette containing the same text. In a new chat, click + by the message box → Add from claudette → claudette, then type your question. Repeat for each conversation.

Either way: if she says "I'm Claude, not…", the instructions didn't load; if she answers but never cites, the connector is off for that chat. The instructions are cached after the first message, so the cost per turn is ordinary.

On first run it downloads the prebuilt core index (~30 MB) from the GitHub release into ~/.claudette/; if that is unavailable it fetches the 36 texts from Project Gutenberg and builds the index itself (a few minutes, once). Then ask:

What would Follett say about a manager who thinks in terms of control?

The model will call search_corpus, read the status, and answer in its own voice with a Sources: line at the end listing every passage it drew on, like [Mary Parker Follett, The New State §412]. Paste a citation back and it can read_passage to show you the surrounding text.

The server also ships a prompt named claudette — her standing instructions — which you can load in clients that support MCP prompts, or paste into a project's system prompt.

Make Claude be Claudette: the skill and the subagent

The connector gives Claude her tools; these give Claude her discipline.

uvx --from git+https://github.com/michaelcpattinson-star/claudette claudette install

That puts two files into ~/.claude/ and one rule into ~/.claude/CLAUDE.md:

  • /claudette skill — a workflow for answering as Claudette in your current session: frame, translate to period vocabulary, search, quote, cite, stop.

  • A routing rule in CLAUDE.md — Claude Code loads this file into every session, and unlike skill and agent descriptions (which are suggestions the model may decline — it will happily say "I'm Claude, not Claudette, but…") it is obeyed: any message addressing Claudette, on any subject, goes to the subagent and comes back verbatim.

  • claudette subagent — a separate agent whose only tools are the connector's six and whose system prompt is her persona and formation. It cannot read your files or the web, so "only from the corpus" is structural. Say "ask Claudette what Follett would make of this plan" and the main session gets back a cited answer it can quote — the second-opinion pattern.

Formation. Claudette has convictions, not just a search box. formation.md is what she thinks — twenty-six positions on power, work, money, care, judgement, machines, reputation, freedom, the body, children, love, age, solitude, grief, land and home, written in the first person, each grounded in named passages and each carried forward by a modern woman thinker verified on Wikidata. It travels in the connector's instructions, so she argues from it and searches only when she wants an author's exact words or meets a question outside it. The corpus is where she learned to think; it is not what she reports on, and she is told never to talk about her shelves. Regenerate or extend it by reading — every line points at its grounds.

No question is out of scope. Diets, drugs, tax, code, football: she answers, as herself. Outside her formation she uses what the model knows the way Claude would, with three differences — where the evidence or the thinking was done by a woman she says so and names her (verified); where one of her convictions touches the question she brings it; and she never hands a question back as "more one for Claude".

Voice. The voice travels with the connector: the server's instructions tell whatever model loads it how Claudette talks, so you get her whether or not the skill or subagent is installed. Claudette answers the way Claude answers — a view in the first sentence, structured by the question, names in the prose rather than as headings, no citations in the body. A Sources: line at the end lists every passage she drew on as [Author, Title §n], plus any attribution from memory marked check. A reader who wants the working finds it in one place; a reader who wants the answer isn't interrupted. She does not talk about "the corpus" unless you ask about it.

Lens mode — beyond the corpus. The corpus ends in the 1920s; the women who wrote about the present did not. So Claudette has two modes, and every answer says which it is using:

  • Cited — verbatim passages from the index, cited to a ref, provable.

  • Lens — the model's own knowledge of women thinkers of any era: Arendt, Ostrom, Jacobs, hooks, Le Guin, Weil, Douglas, Butler. Every idea is attributed to a named woman and a named work; before naming her the model calls verify_attribution, which checks on Wikidata that she exists, is recorded as a woman, and wrote it (Taylor and Weber get refused as men; an invented author gets refused as absent). Paraphrase only, never a quote from memory, and the whole passage is labelled "From memory, paraphrased — check".

The guarantee changes shape between the two: provable in Cited, attributed and checkable in Lens. A reader can always see which they are getting. verify_attribution is the one network call the server makes after setup, and it goes only to Wikidata.

On the present. Claudette does not refuse modern questions. She states in one labelled line what she takes the modern thing to be (or uses your description), finds the pattern underneath — a man who owns other people's work, a system that measures people as inputs, a reputation destroyed in public — searches for it in the corpus's own words, and answers from the passages with the application marked as hers. What she will not do is add facts about the modern thing from outside the corpus.

Getting everything: the full tier

uvx --from git+https://github.com/michaelcpattinson-star/claudette claudette expand

This fetches all 9,000-odd texts from Gutenberg's rsync mirror in one connection (the way Gutenberg asks bulk users to work), strips the licence boilerplate, and builds ~/.claudette/claudette-full.db — a few GB. It is resumable: interrupt it and run it again, and it picks up where it stopped. From then on the server uses the full tier automatically; delete the file to go back to the core. --languages en,fr or --limit 500 for a smaller bite.

Every full-tier hit carries curated: false and the model is told what that means: the edition has not been reviewed by a person, so a preface by someone else may still be in there. The core has been reviewed and trimmed.

Hosting it for others

claudette serve --http --host 0.0.0.0 --port 8000

serves streamable HTTP at /mcp, suitable for a remote connector. Put it behind TLS; the server itself has no auth because it has nothing to protect — it is public-domain text and a search box.


Use it from the command line

uv sync --group chat            # anthropic SDK; needs credentials
uv run claudette ask "What does George Eliot say about unhistoric acts?"
uv run claudette chat            # multi-turn

ask and chat run the same loop the connector would, but with the Anthropic SDK against your own credentials (ant auth login or ANTHROPIC_API_KEY). They add one thing a connector cannot: after each answer, every citation is checked against the passages actually retrieved that turn, and any that do not match are printed as unverified. That is the difference between "cites sources" and "produces citation-shaped text".

No model is needed for the corpus itself:

uv run claudette fetch           # download the core from Gutenberg → ~/.claudette/texts
uv run claudette verify --show 3 # check each header matches the manifest; eyeball the openings
uv run claudette index           # build the core: ~/.claudette/claudette.db
uv run claudette expand          # build the full tier: ~/.claudette/claudette-full.db (hours, GBs)
uv run claudette search "power over" -k 3
uv run claudette read follett-new-state§412
uv run claudette works --author gaskell   # ~ marks unreviewed full-tier editions
uv run claudette authors nurs             # who is in here, and how much
uv run claudette install         # skill, subagent and CLAUDE.md rule into ~/.claude
uv run claudette export-prompt   # PROJECT_INSTRUCTIONS.md for a desktop/claude.ai Project
uv run claudette catalog         # maintainers: regenerate authors.csv and works.full.csv

How the guarantee is enforced

There is no classifier guessing whether a text was written by a woman. There are two lists, and the index is built from them and nothing else.

The core list — corpus/manifest.toml. Every entry names its author, its Gutenberg ID, and one or two sentences on why it is there. A reviewer can read the whole thing in five minutes, which is the point.

The full list — src/claudette/data/works.full.csv, generated by catalog.py from two public sources:

  1. Wikidata: every item with a Project Gutenberg author ID whose sex or gender is recorded as female. The query is in the code; the result is authors.csv with a Wikidata ID on every row, so any author can be checked in one click.

  2. Gutenberg's own RDF metadata: a text qualifies only if every creator, editor, translator and contributor is on that list. A woman's novel translated by a man is his prose; a woman's letters edited by a man carry his introduction. Both are excluded. Illustrators are not prose and are ignored. Anonymous and unattributed works are excluded.

The rule is stricter than the hand-curated core: it rejected three of the core's own editions (Fuller's, edited by her brother with an introduction by Horace Greeley; Goldman's, with a biographical sketch by Hippolyte Havel; Taylor Mill's), which is how those two prefaces came to be trimmed. What the rule cannot do is read the text: a full-tier edition may still carry front matter by another hand that Gutenberg's metadata did not record. The core has been read; the full tier has not.

Around the list:

  • Validation refuses an entry without an author. An unattributed passage is exactly what this project exists to rule out, so it cannot load.

  • claudette verify re-checks every downloaded text's header against the manifest title, so an ID typo cannot silently pull in the wrong book.

  • Editorial front matter is trimmed by declared markers, and a declared marker that is not found is an error, not a silence. Gutenberg editions sometimes carry prefaces by editors, and some editors were men.

  • Every tool response is stamped with provenance by the envelope, not by the tool, so no code path can omit it.

  • no_coverage is a status, not an empty list. A model handed [] narrates it as "they had nothing to say". The status makes the difference between "nothing matched" and "the corpus does not cover this" structural. There is a weak status too, for a thin match that should be reported as thin.

Texts and indexes live in ~/.claudette/ and are not committed: the core is reproducible with claudette fetch && claudette index, the full tier with claudette expand, and the catalogue itself with claudette catalog.

The core corpus

Twenty-seven authors, two shelves. Full list with reasons in the manifest; list_works returns it at runtime.

Thought — Follett, Addams (×2), Martineau (×2), Gilman, Schreiner, Wollstonecraft, Fuller, Harriet Taylor Mill, Astell, Goldman, Wells, Tarbell, Nightingale, Jacobs, Sojourner Truth.

Fiction — Gaskell, Austen (×2), Mary Shelley, the three Brontës, George Eliot (×2), Alcott, Stowe, Chopin, Gilman (×2), Wharton (×2), Woolf (×3).

Known limits, stated rather than hidden

  • Public domain means the corpus mostly ends in the 1920s. It is heavily English-language (7,924 of the 9,048 full-tier texts) and it is what volunteers chose to digitise, which is its own bias.

  • The full tier's gate is Wikidata. An author nobody has entered there, or entered without a gender, is invisible to it. The 2,447 is a floor, not the truth.

  • Retrieval is BM25 over passages (SQLite FTS5, Porter stemming). It matches words, not ideas; the persona prompt tells the model to retry with period vocabulary ("sympathy" for "empathy", "master and men" for "management"). No embeddings, by choice: the index can be rebuilt by anyone from the standard library and a search result can be reproduced by hand with sqlite3.

  • Front-matter trimming is per-work and manual. claudette verify --show 5 exists so a reviewer can look.

  • Lens mode verifies identity, not content: Wikidata confirms that Ostrom exists, is a woman, and wrote Governing the Commons; it cannot confirm that the paraphrase of her argument is right. That is why Lens passages are labelled check and never quoted verbatim.

  • The evals in evals/ exist and are wired, and have not yet been run. evals/results/README.md says so. Numbers appear when someone runs them.


Adding a work

To the core (reviewed, shipped in the release index):

  1. Find it on Project Gutenberg. Confirm the author.

  2. Add a [[work]] entry to the manifest: id, slug, author, title, year, shelf, why. Add start_after / end_before if the edition has front or back matter by another hand.

  3. claudette fetch && claudette verify --show 5 && claudette index.

  4. pytest. The manifest tests will tell you if the entry is malformed.

  5. Open a pull request. The why line is the review.

To the full tier: it is generated, so the fix is upstream. If a woman author is missing, add her sex or gender to Wikidata and her Gutenberg author ID (P1938); claudette catalog picks her up on the next run. If a work is wrongly excluded, it is usually an editor or translator whose gender Wikidata does not record — same remedy.

Layout

src/claudette/
  data/manifest.toml   the core list. Symlinked at corpus/manifest.toml for reviewers.
  data/authors.csv     women on Wikidata with Gutenberg author IDs (generated)
  data/works.full.csv  every qualifying Gutenberg text (generated)
  manifest.py          loads and validates the core list
  catalog.py           builds the full list from Wikidata + Gutenberg metadata
  expand.py            fetches and indexes the full tier locally
  fetch.py             Gutenberg download + boilerplate stripping (the only network code)
  chunk.py             paragraphs → citeable passages
  index.py             SQLite FTS5 build and query; the refusal rule
  envelope.py          uniform response shape; provenance written here, not by tools
  bootstrap.py         first-run: prebuilt index or local build
  attribution.py       Lens mode's check: is she real, a woman, and did she write it (Wikidata)
  server.py            the MCP server. Six tools, one prompt. No key.
  persona.py           Claudette's standing instructions (voice + rules)
  data/formation.md    what she thinks — first person, grounded, carried forward
PROJECT_INSTRUCTIONS.md  persona + formation, ready to paste into a Project (generated)
  chat.py              CLI chat client — the only module that calls a model
  cli.py               `claudette` command
tests/                 offline; builds a fixture corpus the same way as the real one
evals/                 questions, runner, mechanical scorer

Licence

MIT for the code. The texts are public domain via Project Gutenberg; the Gutenberg licence header and footer are stripped from the indexed text and never leave your machine in either direction.

Available Tools

6 tools
corpus_provenanceA

State what this corpus is, where it came from, how it was curated, and its known limits.

Use when the user asks what Claudette is, whose words these are, or how the guarantee is enforced.

Inputs: no named parameters. Returns: data, status, constraint, provenance, +1 more

list_authorsA

Find which women are in the corpus and how much of each: name, works, passages, curated.

Use when the user asks 'is X in there?' or 'who do you have on Y?'. Not a
passage search — pair with search_corpus once you know the name.

Inputs: limit, query. Returns: data, status, constraint, provenance, +1 more

list_worksA

List works in the corpus: author, title, year, why it is included, source, and slug.

Use to tell the user what the corpus holds, or to pick a slug for a
restricted search. Not a search — it returns no passages. For the full
tier, filter by author; use list_authors to find her name first.

Inputs: limit, shelf, author. Returns: data, status, constraint, provenance, +1 more

read_passageA

Return one passage verbatim, with its neighbours, for quoting or checking a citation.

Use after search_corpus when you need the surrounding text. Not for finding
passages — it takes a ref, not a question.

Inputs: ref (required), context. Returns: data, status, constraint, provenance, +1 more

search_corpusA

Find passages across the corpus that bear on a question.

Call this before answering anything of substance, then answer AS Claudette
(see the server instructions: your own voice, view first, no citations in
the body, a Sources: line at the end). Returns ranked passages, each with a
citation `ref` and the query terms it actually contains. Not for reading a
passage you already have a ref for — use read_passage.

Inputs: query (required), k, work, language, +1 more. Returns: data, status, constraint, provenance, +1 more

verify_attributionA

Check against Wikidata that a person exists, is recorded as a woman, and wrote the named work.

Lens mode only: call this BEFORE naming any author or work from memory
rather than from the corpus. `ok` means name her. `weak` means name her
with the stated caveat. `not_found` means do not. Not for authors already
in the corpus — search_corpus is their check. The one network call this
server makes; it goes only to Wikidata.

Inputs: name (required), work. Returns: data, status, constraint, provenance, +1 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct job: search_corpus finds passages by question, read_passage retrieves a known ref, list_works/list_authors expose metadata, corpus_provenance explains the corpus, and verify_attribution handles inbound Wikidata checks. The descriptions explicitly warn against cross-use, so an agent should not confuse them.

    Naming Consistency4/5

    Five of six tools follow a clear snake_case verb_noun pattern (search_corpus, read_passage, list_works, list_authors, verify_attribution). corpus_provenance breaks the pattern as a noun phrase rather than a verb, but the naming remains predictable and easy to skim.

    Tool Count5/5

    Six tools is well-scoped for a read-only corpus assistant: search, passage lookup, two metadata views, provenance, and verification. Each tool has a clear role and none feels redundant or like filler.

    Completeness5/5

    The surface covers the full user workflow for this domain: discover works/authors, search passages, read passages verbatim for citation checks, explain corpus provenance, and verify external attributions. No create/update/delete operations are needed because the corpus is curated and read-only.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to answer SEO, local SEO, blogging, and Etsy questions strictly from a governed knowledge base of cited course material, declining anything outside its scope.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables cited research synthesis from verified public sources, returning extractive quotations with source URLs and refusing topics that cannot be grounded.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to search and retrieve historical materials from five public archives in a unified format, including full-text search inside scanned books, rights statements, and provenance-tracked media downloads.
      23
      MIT