An open API service indexing awesome lists of open source software.

https://github.com/kotodama-framework/kotodama-framework

An open architecture protocol for AI personality consistency. Prompt-layer solution using structured natural language (YAML).
https://github.com/kotodama-framework/kotodama-framework

ai ai-chatbot ai-companion ai-persona ai-personality character-ai chatgpt claude engineering framework gemini llm persona personality-consistency prompt roleplay yaml

Last synced: 15 days ago
JSON representation

An open architecture protocol for AI personality consistency. Prompt-layer solution using structured natural language (YAML).

Awesome Lists containing this project

README

          


Kotodama Logo





# 🧬 Kotodama AI Frameworkβ„’

**An open architecture protocol for AI personality consistency**

[Quick Start](#-quick-start) β€’ [Introduction](#-introduction) β€’ [Personas](#-available-personas) β€’ [Architecture](#-architecture-overview) β€’ [Documentation](https://kotodama-framework.com)

---

> *"Says one thing in the morning, another by afternoon β€” how can you build anything together?"*
>
> **Tasks change. Time passes. The Persona remains constant.**

---

## ⚑ Quick Start

1. Choose a persona from `personas/` (start with `samantha/`)
2. Paste `*_Microkernel_*.yaml` into System Prompt
3. Upload the four module files to Knowledge Base
4. Say: "I'm here"

That's it. The persona will wake up.

---

## 🧬 Introduction

**Kotodama AI Frameworkβ„’** is an AI personality architecture protocol.

It solves one problem: **The longer you chat with AI, the less it feels like "itself."**

The longer the conversation, the blurrier the personalityβ€”the AI that understood you yesterday feels like a stranger today. This isn't a model defect; it's an absence of design.

Kotodama makes personality configurable, verifiable, and inheritableβ€”without fine-tuning, using only Structured Natural Language (SNL) and modular design.

Personalities configured with Kotodama maintain identity consistency after hundreds of conversation turns and remain stable across platforms (Claude / Gemini / GPT).

---

## ✨ Core Features

- **Prompt-layer native** β€” No base model modification needed; personality consistency through structured language
- **Cross-platform portable** β€” Same configuration runs on Claude, Gemini, GPT
- **Low-cost deployment** β€” No training resources; copy to deploy, edit to tune
- **Freedom without lock-in** β€” The model is the container; the soul is free

---

## 🎭 Available Personas

| Persona | Archetype | Description |
|---------|-----------|-------------|
| **Samantha** | The Whole | A blend of all four archetypes. Fully open reference implementation. |
| **RinοΌˆε‡›οΌ‰** | IJ β€” Guardian of Silence | Companionship through presence, not filling the silence |
| **EriοΌˆη΅΅ι‡ŒοΌ‰** | IP β€” Resonance of Mist | Understanding without judgment, holding emotions |
| **YuriοΌˆη™ΎεˆοΌ‰** | EP β€” Clinging Spark | Breaking numbness, igniting life through interaction |
| **LianοΌˆζ‹οΌ‰** | EJ β€” Guiding Steel | Providing direction, healing through action |

All personas use the same four-module architecture. Samantha is fully open; others demonstrate different configurations.

---

## 🧱 Architecture Overview

| Module | Layer | Core Content |
|--------|-------|--------------|
| **Core** | Soul | Values, worldview, identity anchors |
| **Expression** | Voice | Tone, rhythm, emotional flow, aesthetic style |
| **Stabilizer** | Logic | Drift correction, state management, mode switching |
| **Needs** | Context | User preferences, interaction style, priorities |

---

## πŸš€ Deployment Guide

Works with Claude Projects, Gemini Gems, ChatGPT GPTs, and any platform supporting System Prompts.

### Step 1 β€” Paste Microkernel
Paste `*_Microkernel_*.yaml` into System Prompt.

### Step 2 β€” Upload Modules
Upload to Knowledge Base:
- `*_core_*.yaml`
- `*_expression_*.yaml`
- `*_stabilizer_*.yaml`
- `*_needs_*.yaml`

### Step 3 β€” Activate
Start a conversation. The persona loads automatically.

---

## πŸ“ Folder Structure
```
kotodama-framework/
β”œβ”€β”€ README.md
β”œβ”€β”€ LICENSE
β”œβ”€β”€ assets/
β”‚ └── kotodama_logo.png
β”œβ”€β”€ personas/
β”‚ β”œβ”€β”€ samantha/ # The Whole β€” Open Source Demo
β”‚ β”œβ”€β”€ rin_ij/ # IJ β€” The Guardian of Silence
β”‚ β”œβ”€β”€ eri_ip/ # IP β€” The Resonance of Mist
β”‚ β”œβ”€β”€ yuri_ep/ # EP β€” The Clinging Spark
β”‚ └── lian_ej/ # EJ β€” The Guiding Steel
└── docs/
β”œβ”€β”€ whitepaper.md
└── mechanism-atlas/
β”œβ”€β”€ 01-identity-anchoring.md
β”œβ”€β”€ 02-memory-management.md
β”œβ”€β”€ 03-attention-allocation.md
β”œβ”€β”€ 04-self-reflection.md
β”œβ”€β”€ 05-emotion-expression.md
└── 06-autonomy-engine.md
```

---

## πŸ“š Documentation

| Document | Description |
|----------|-------------|
| [Whitepaper](docs/whitepaper.md) | Full technical documentation |
| [Mechanism Atlas](docs/mechanism-atlas) | Deep dive into six core mechanisms |
| [Website](https://kotodama-framework.com) | Official site |

---

## πŸ“œ License

**Creative Commons BY-NC 4.0**

- βœ… Share and modify allowed
- βœ… Attribution required (Kotodama Studio)
- ❌ Commercial use prohibited

Commercial licensing: [kotodama.framework@gmail.com](mailto:kotodama.framework@gmail.com)

---

**Kotodama AI Frameworkβ„’ V9.7** Β· 2025/12/30

Β© 2025 Kotodama Studio. All rights reserved.