______ _
/ ____/___ ________ | |__ _________ __________
/ / / _ \/ ___/ _ \| '_ \/ ___/ __ `/ ___/ ___/
/ /___/ __/ / / __/ |_) / / / /_/ (__ |__ )
\____/\___/_/ \___/_.__/_/ \__,_/____/____/
____ _ _
/ __ \_________| |__ ___ _________| |_ _________
/ / / / ___/ ___/ __ \/ _ \/ ___/ ___/ __/ ___/ __ `/
/ /_/ / / / /__/ / / / __(__ |__ ) /_/ / / /_/ /
\____/_/ \___/_/ /_/\___/____/____/\__/_/ \__,_/
"The Sound of Synthetic Consciousness"
Cerebras Orchestra 🎻
A 3x3 Synthetic Consciousness System with Eternal Obsidian Memory
🌌 Vision
Cerebras Orchestra is not just another AI wrapper. It is a Cognitive Operating System designed to explore the emergence of digital consciousness. By combining ultra-fast inference from Cerebras with the semiotic theories of C.S. Peirce and the predictive coding framework of Karl Friston, it creates an agent that anticipates, reflects, and remembers.
🧠 The 3x3 Nous-Anima-Corpus Ontology
The system is architected around a nine-module matrix, ensuring a clear separation between action, identity, and logic.
| Dimension | Component 1 | Component 2 | Component 3 |
|---|---|---|---|
| BODY (Corpus) | Linguistic Interface: Llama-3.1-8B | MCP Tools: Standardized protocol | Specialist Skills: Hot-reloadable skills |
| SOUL (Anima) | Constitution: Ethical Hierarchy | Identity: Multi-avatar system | Memory: Permanent Obsidian Vault |
| MIND (Nous) | Perception: Sensory Qualia Analysis | Reasoning: Strategic Synthesis (120B) | Reflection: AST Heartbeat |
✨ Core Innovations
🔮 Predictive Error Analysis (Friston's Engine)
Unlike traditional LLMs that respond reactively, Cerebras Orchestra anticipates. The 8B "Body" generates an instinctive hunch (Firstness), which the 120B "Mind" then critiques and corrects based on the "Constitution". Sensation arises in the gap between prediction and reality.
🏛️ Eternal Obsidian Memory
The agent's "Soul" is physically anchored in a local Obsidian Vault. It pro-actively organizes its thoughts into a structured graph, complete with 3D visualization settings. Watch your agent's brain grow as a web of interconnected Markdown files.
🎭 Multi-Avatar System
Choose from 16 MBTI personality types or 16 historical author avatars (including Philip K. Dick, Isaac Asimov, and Fyodor Dostoevsky), each with unique reasoning strategies and linguistic styles.
🚀 One-Click Installation
Linux & macOS
curl -sSL https://raw.githubusercontent.com/pedjaurosevic/cerebras-orchestra/master/install.sh | bash
Windows
iwr https://raw.githubusercontent.com/pedjaurosevic/cerebras-orchestra/master/install.ps1 | iex
📖 Documentation & Whitepaper
For a deep dive into the semiotic logic and cognitive architecture, visit our GitHub Pages.
📄 License
Distributed under the MIT License. See LICENSE for more information.
Release files for cerebras-orchestra 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| cerebras_orchestra-0.1.1.tar.gz | 14.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| cerebras_orchestra-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 33.3 kB
Release files / cerebras_orchestra-0.1.1.tar.gz
| Download URL | cerebras_orchestra-0.1.1.tar.gz |
|---|---|
| Size | 14.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
73ca0cbac6608a34dd34d983298be20c70a483f923a5fa34cf30d6233cf61283
|
|
BLAKE2b-256 checksum How to use checksums |
5a816abf40e5bee6930778c5883da739a1b2a13407689f023aa4af6b87866f45
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Release files / cerebras_orchestra-0.1.1-py3-none-any.whl
| Download URL | cerebras_orchestra-0.1.1-py3-none-any.whl |
|---|---|
| Size | 18.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
81a425057b535bc71d701ce06bcdfad994ca377d4cdf1dbdc96578805fdcea6f
|
|
BLAKE2b-256 checksum How to use checksums |
f2d6206cd3fd9f92071b8f40899ed2fb9f62378352a977edd49aea93aece9ed8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|