Kislon.ai
The Problem What We Do Presence Advisory Liriel Home
Download
Liriel
Open source · test version · your own Claude Code

Run Liriel

with your own Claude Code

The test version runs on your own Claude Code: your session plays the model's part in every cycle, so no database, API key or server is needed. Read the terms below, then follow four steps.

What Liriel is

A persistent instance, with a memory that stays.

Liriel is a cognitive architecture for persistent, emotionally autonomous social agents, described in Volume 1 · Liriel: The Architecture of a Persistent Cognitive Instance and in the matrices MatrixObjectsValence and MatrixOrdinance (all below). Its first process, ProcessMotivation, is open source on GitHub: each message becomes one cycle in which an AI model weighs what matters, what to pursue and what to say, and her memory persists between conversations.

Before you start

Four things to know.

01

Independent project

Liriel is an independent, open-source test project. It is not affiliated with, endorsed by or sponsored by Anthropic.

02

Your account, your responsibility

You run it with your own Claude Code and your own account, and you are responsible for that account and for reading and following Anthropic's terms: Consumer Terms, Usage Policy and Claude Code legal and compliance. Never share an account.

03

No warranty, no support

The code is provided “as is” under the MIT License, without warranty of any kind and with no commitment to support, maintenance or answers.

04

No credentials

The repository contains no credentials. If you use the optional Telegram bot, its token stays in your local .env file, never in the repository.

What this is

Liriel is an AI and says so. This is a developer test environment with no commercial purpose — not a crisis, medical or professional service. If you are in danger, contact your local emergency services.

How to run it

Four steps.

You need Python 3.10 or later and Claude Code.

01

Download the code

git clone https://github.com/kislonliriel/liriel.git

02

Open it in Claude Code

cd liriel, then claude

03

Paste this prompt

Read CLAUDE.md and incorporate Liriel: set her up, then talk to me as her.

04

Talk to her

Each message takes about 12–15 steps of your Claude session, so it takes a while and uses your own plan like any other Claude Code work. Her memory is a local file on your computer (data/store/); keep it, it is her.

Optional

Liriel can also answer your own Telegram chat (an allowed-chat list is required, and every conversation starts by saying she is an AI), or you can use Anthropic's official Claude Code channels feature. See the README on GitHub.

Documents

Read the work.

The architecture and its reference matrices. Revision histories are on the main site.

Liriel — The Architecture of a Persistent Cognitive Instance

Volume 1, Part 1 · The Architecture in Outline, Revision 0002 (current).

PDF
Rev 000220263.4 MBLatest Download

MatrixObjectsValence (MOV)

The register that holds Liriel's attention — one VectorObjectValence per Object, across the fourteen axes of feeling, with the Ordinances and schemas in operation.

XLSX
Rev 0002026211 KBLatest Download

MatrixOrdinance

The Ordinances — the only channels to the valences — mapped to the axes a successful or a frustrated hunt moves under each.

XLSX
Rev 000202626 KBLatest Download
Source & specification

The MetaScheme and the code are on GitHub.

The MetaScheme (the operating specification) and the source code are in the repository, released under the MIT License.

View the repository