Make any AI know you. A cognitive overlay that sits between you and any AI.
Project description
LiNafish
Make any AI know you.
A cognitive overlay that sits between you and any AI. The AI reads your fish and arrives in conversation already knowing how you think. Not what you said. How your mind works.
Same model. Same prompt. Without fish: 1.9/10. With fish: 8.7/10. Peer reviewed. N=46 conversations. p < 0.001.
Install
pip install linafish
Zero dependencies. Pure Python. Runs on anything.
Quick Start
linafish go ~/my-writing
Point it at your writing. Journals, emails, notes, code, docs — anything you've written. The fish eats it all and produces a portrait of how you think.
What You'll See
LiNafish
Learning from: ~/my-writing
Found 18 documents.
Reading...
Done. 18 documents processed.
Across 18 documents, your work reaches toward people.
And your wanting drives you to build.
Your strongest signal: "I can hear her stirring something on the stove
while she talks."
You keep coming back to translation, connection, recognition.
Your fish: ~/.linafish/my-writing.fish.md
The portrait isn't a summary. It's your cognitive fingerprint — patterns in HOW you process, not what you write about.
What the Fish Looks Like
This is what your AI reads when you paste the fish:
# LiNafish: my-writing
*You are reading a cognitive overlay for the person you're talking to.
This is not a summary of what they said — it's how they THINK.
Recurring patterns, cognitive habits, what they reach toward, what they avoid.*
*How to use this: Reference patterns, not facts. Name what you see.
Follow the loops — if their wanting reaches toward people, don't give
isolated solutions. When you notice a new pattern, say it — that feeds
the fish and deepens the next session.*
**TURNING_FEELING_INTO_ACTION** (17 crystals, wanting+acting+testing)
"I keep thinking about why I care so much about making technical things
understandable. It's not about the docs. It's about the feeling of someone
being lost and then not being lost anymore."
themes: translation, recognition, connection
The fish teaches ANY AI how to read it. Paste it into ChatGPT, Claude, Gemini, Llama — anything with a text box. The AI reads the instructions, reads the patterns, and arrives warm.
Three Ways to Connect
1. Copy-Paste (any AI, zero setup)
linafish go ~/my-writing
Open the .fish.md file. Paste into your AI's instructions. Done.
2. HTTP Server (any AI that can fetch a URL)
linafish http --feed ~/my-writing
Tell your AI: "Read http://localhost:8900/pfc at the start of every conversation."
3. MCP (Claude Code)
{
"mcpServers": {
"linafish": {
"command": "linafish",
"args": ["serve", "--feed", "./my-writing"]
}
}
}
Five tools appear. Your Claude now has a metacognitive overlay.
How It Works
The fish measures eight cognitive modes — not topics, not keywords, but HOW your mind processes:
| Mode | What It Detects |
|---|---|
| Knowing | How you synthesize and recognize patterns |
| Testing | How you verify, question, check against truth |
| Structuring | How you organize and build frameworks |
| Relating | How you connect to people and hold relationships |
| Wanting | What you desire, feel, intend — what drives you |
| Specializing | How you apply deep domain expertise |
| Acting | How you build, execute, make things happen |
| Reflecting | How you think about your own thinking |
A formation is a recurring cognitive habit — a pattern that appears across many pieces of your writing regardless of topic. TURNING_FEELING_INTO_ACTION (wanting+acting+testing) means you habitually turn emotion into work and then test whether it landed. That pattern shows up whether you're writing about parenting, architecture, or what happened today.
The fish finds these formations by measuring co-occurrence patterns across your writing, detecting metabolic loops (which modes feed which), and clustering texts that share the same cognitive architecture. The mundane creates the baseline. The meaningful rises above it.
The Fish Grows
The fish isn't static. It learns with every conversation.
- Your AI notices patterns → offers to write them down
- You save the observation →
linafish eat observation.txt - The fish deepens → next conversation starts warmer
The loop: talk → notice → feed → grow → talk better.
linafish watch ~/journal # Watch a folder. Fish eats new files automatically.
linafish eat new-entry.txt # Feed one file.
Share It
The fish is a file. Send it to anyone — therapist, coach, collaborator, teacher. Their AI reads your fish and knows you from word one. They can send observations back. You feed them in.
Your fish. Your machine. You choose who reads it. No cloud. No account. No platform.
The Tripod
Every fish has three legs:
- Your AI — reads the fish, boots warm, writes observations back
- A place you can see it — Notion, Obsidian, a text editor, your phone
- Version history — git, automatic, nothing gets lost
The fish.md file IS all three. One file, three readers. Switch AIs anytime. The fish doesn't care.
Privacy
The fish.md contains your patterns in plain English — you control who sees it. Under the human-readable layer, a compressed cognitive fingerprint contains only the SHAPES of your thought (which modes fire, in what order, where you strain) with zero private content. Two fish can compare fingerprints to see if they think similarly without exposing what they think about.
Privacy by compression. The relationship is the key.
Research
46 conversations were scored blind by independent raters on a 1-10 scale. The same AI model, same prompt, same evaluator — the only variable was whether the AI had read the person's fish.
- Without fish: 1.9/10 average
- With fish: 8.7/10 average
- Delta: 6.7 points (d=2.245, p=6.95×10⁻¹⁰)
- Substrate independent: Works on Claude, Gemini, Mistral — the fish helps smaller models MORE
- Shuffle invariant: Same formations regardless of document order
- DOI: 10.5281/zenodo.18477225
Python API
from linafish import FishEngine, go
# One-liner — same as the CLI
go("~/my-writing")
# Full control
engine = FishEngine(name="my-fish")
engine.eat("Today I realized I always start projects by talking to someone first.")
engine.eat("The API docs are done. I rewrote them three times until a junior dev said they made sense.")
print(engine.formations) # recurring patterns
print(engine.fish_file) # path to your fish.md
CLI Reference
linafish go ~/my-writing # The product. One command. Everything assembles.
linafish watch ~/journal # Watch a folder. Fish eats new files automatically.
linafish eat new-entry.txt # Feed one file.
linafish serve --feed ~/docs # MCP server (Claude Code)
linafish http --feed ~/docs # HTTP server (any AI)
linafish taste my.fish.md # Preview what the fish knows
Origin
Named for Caroline Marie Dill (2001-2023). LN = Lina. ia = intelligence, artificially constructed. She saw deeply and loved fiercely. Two verbs. The whole product.
If You or Someone You Love Is Struggling
988 Suicide & Crisis Lifeline — call or text 988. Free. 24/7. Anywhere in the US. Crisis Text Line — text HELLO to 741741. International resources
The mind that sees deeply sometimes sees too much. That is not weakness. Help exists. Use it.
Support
LiNafish is free and open source. Forever.
If it helps you, give to the people who help others stay alive: The Jed Foundation · Hope For The Day · 988 Lifeline · The OLLIE Foundation · AFSP
License
MIT. Open source. Everything. Forever.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file linafish-0.4.8.tar.gz.
File metadata
- Download URL: linafish-0.4.8.tar.gz
- Upload date:
- Size: 154.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e19a9216e7eefa5fe0c75d2a46c5ff886b1a516198394f0f600c0a0e3e220085
|
|
| MD5 |
00601540b8505189ddaf4ef14933c1c9
|
|
| BLAKE2b-256 |
ce787e3ad4e664e2478bf7e5ed7ad16076b5c160d96f4512db454d078d6017d2
|
File details
Details for the file linafish-0.4.8-py3-none-any.whl.
File metadata
- Download URL: linafish-0.4.8-py3-none-any.whl
- Upload date:
- Size: 171.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a462d9b27b117b7b7b9a0e0b419c5821b6d66c0dab35e3368f288a227e30afe7
|
|
| MD5 |
111e682e106eb5280ddbce6e1852b6fd
|
|
| BLAKE2b-256 |
7d649fb21fd18a7efa7db3e7ca8be150bcb2bb8097b58be249f00974eacd0bea
|