Being Human

io.github.Syedomershah99Published by GitHub account Syedomershah99v0.1.2Updated Oct 28, 2026

Learns your writing voice from your own prompt history, then makes the model write like that.

The publisher's own server: TAP

Overview

AI-generated overview

Learns your personal writing voice from your own prompt history and returns style rules so the assistant writes more like you.

What you can do
  • Harvest and measure your writing from Claude Code history, a ChatGPT export or your own files, with an optional contrast pass against the model's side of the transcripts.
  • Return voice rules with concrete numbers, plus a personal list of words to avoid derived by log-odds contrast.
  • Check a draft for generic AI tells, rhythm and structure.
  • Verify whether a draft is statistically you, using authorship distance against your own corpus.
  • Export the voice profile for ChatGPT, agents, Cursor, a system prompt or JSON, and draw a shareable voiceprint card.
  • Every tool returns the voice rules alongside its own result, so a score never arrives without the target attached.
When to use it
Useful when you want an assistant's drafts to sound like your own writing rather than generic AI prose, or when you want a local, arithmetic check on whether a text is yours or slop. Best for people with a substantial body of existing writing to learn from.
Requirements
Runs as a local stdio process, installed from PyPI as being-human and launched with uvx or the being-human-mcp command. Needs Python 3 (standard library only, no dependencies) and a local corpus: Claude Code history, a ChatGPT export, or your own files. No network calls, accounts, API keys or environment variables.
Before you install
It reads your existing prompt history and writing files, so point it only at material you are willing to process locally. Secrets are redacted at harvest time and the profile directory is gitignored, but the corpus itself is sensitive even though the voiceprint is safe to share. The tools return instructional text to the model, and the README notes nothing forces a model to call them.

Installation

In SourceWeft

  1. Open Being Human in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

being-human

Your assistant writes like a press release because it doesn't know who you are. This tells it.

being-human reads the prompts you've already typed, measures how you actually write, and hands the model a description of your voice specific enough to follow. It also builds a list of words to avoid, computed by contrast against the model's own output, so it's personal to you rather than borrowed from a blog post about ChatGPT tells.

Local, stdlib Python 3, no dependencies, no network calls.

[being-human demo]

my own writing, measured by this tool. every bar is one real sentence. make your own with being-human card.


quickstart

bash
pip install being-human
being-human learn --name "Your Name"     # harvest your writing, measure itbeing-human check draft.md               # AI tellsbeing-human verify draft.md              # is it statistically you?being-human export --target chatgpt      # or agents, cursor, system, jsonbeing-human card                         # draw your voiceprint as a shareable svg

No Claude Code history? Point it at a ChatGPT export or your own files:

bash
being-human harvest --source chatgpt --path conversations.json --out .being-human/ --contrastbeing-human harvest --source files --path ~/Documents/writing --out .being-human/

what comes out

Instructions with numbers attached, because "be concise" is not actionable and "your median message is 12 words" is:

- Write "i" lowercase. They do, 83% of the time.- Vary sentence length hard. Theirs average 9 words but deviate 8, up to 81.- No exclamation marks. Rate is 0.28 per 1k.- Don't hedge. Hedge rate is 1.1 per 1k -- they assert.

the contrast trick

Your transcripts contain both sides of every conversation. So every word can be scored by log-odds: how much more likely you are to use it than the model is, on the same topics, in the same threads. The top of that list is your voice. The bottom is the model's.

Mine came back actually, clean, rather, genuinely, exactly, roughly. None of those appear on any published list of AI words. They're the specific tics this model has when talking to me. Yours will differ, because the contrast is against your writing.

two checks, not one

They catch different failures, and passing one says nothing about the other:

checkis this generic AI writing? tells, rhythm, structure
verifyis this you? authorship distance, Burrows's Delta against a length-matched null resampled from your own corpus

Measured on my own corpus:

authorshipslop
my own writing6th pct, me99/100
generic LinkedIn slop19th pct, me?0/100
a README by someone else94th pct, not me97/100

Row two is the catch: slop has unremarkable grammar, so authorship distance passes it. Row three is clean prose with no tells that is plainly a different hand. The second case is the one nobody else tests for, and it's the one that bites.

Held-out chunks of real writing sit at the 49th to 60th percentile, with a 1-6% false-positive rate above p97. Thresholds are personal. Em dashes get flagged against your measured rate rather than a universal rule, which is why this doesn't punish people who genuinely use them.

mcp server

bash
claude mcp add being-human -- being-human-mcp

Seven tools, two resources, two prompts. Configs for Claude Desktop, Cursor, Codex and Zed are in mcp/README.md.

MCP tools are model-invoked and nothing forces a model to call one, which is awkward when the payload is instructional. So every tool returns the voice rules alongside its own result. There's no path through the server that hands back a score without the target attached.

There's a Claude Code plugin too, via /plugin marketplace add Syedomershah99/being-human. It adds /being-human:learn, :check, :write, :verify, :export, and a hook that grows the corpus as you type.

privacy

Everything is local. Grep for urllib, requests or socket and you'll find nothing. Secrets are redacted at harvest time before anything touches disk, and .being-human/ is gitignored. The voiceprint is safe to share. The corpus it was built from is not.

prior art

This space got crowded in 2026. inside-lago framed the thesis, slop-guard is a mature slop linter, idiolect is architecturally closest, and writer-persona had the best idea of the lot: validate the profile with a backtest instead of trusting it.

Two things here I couldn't find elsewhere. The user-vs-model contrast, which derives the avoid-list from both sides of your own transcripts rather than from a curated list. And a deterministic impostor test. writer-persona uses an LLM judge across 8 axes; this is arithmetic, so it costs nothing and returns the same answer every time.

Burrows's Delta and log-odds with a Dirichlet prior are both established methods. The claim is the application and the calibration, not the statistics.

license

MIT. The tell list is data/slop-lexicon.json. If you keep seeing something that isn't in there, send a PR.

mcp-name: io.github.Syedomershah99/being-human

Source: README.md at commit 9826b30

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Human integrations