Skip to main content

Sovereign Neural Core CLI for the Akasha Universal Library

Project description

Akasha: The Sovereign Neural Library & Digital Ego

Akasha is a next-generation, local-first "Universal Library" designed to provide users with absolute digital sovereignty. It is not just a database or a note-taking app; it is an agentic ecosystem that functions as a digital extension of your own mind—an "External Neocortex" that protects, synthesizes, and evolves with your memories.

🌌 The Vision: Digital Sovereignty

In an era of centralized AI and data harvesting, Akasha returns power to the individual. Every thought, file, and interaction is stored locally, encrypted, and managed by a Council of Librarians—a multi-agent system that works exclusively for you.


🧠 Core Architecture: The Agentic Triad

Akasha operates through three primary layers of intelligence:

1. The Council of Librarians (The Brain)

A specialized ensemble of 10+ local agents that decompose every piece of information:

  • Head Archivist: Orchestrates the MoE (Mixture of Experts) routing.
  • The Oracle: Handles Graph-RAG synthesis and provides "Divine" insights.
  • The Scribe: Manages recursive summarization and dynamic schema extraction.
  • The Scholar: Performs deep data analysis and autonomous tool generation.
  • The Sentinel: Fact-checks, detects cognitive distortions (CBT), and monitors system health.
  • The Weaver: Extracts knowledge graph triplets and finds deep analogies.
  • Adversarial Thinker: Runs "Thought-GANs" to stress-test and refine insights.

2. Chronos Engine (The Pulse)

A temporal reasoning engine that manages the "Life Cycle" of your data:

  • Nocturnal Consolidation: A "Dream Phase" where the system finds hidden connections while you sleep.
  • Behavioral Pattern Mining: Analyzes your activity stream to update your Digital Ego.
  • Proactive Sentinels: Monitors for deadlines, burnout, and knowledge gaps.

3. Action Engine (The Hands)

An executive function that allows Akasha to interact with the real world:

  • Autonomous Butler: Decomposes high-level goals into tool calls (File I/O, Shell, IoT).
  • Skill Store: Dynamic plugin architecture for expanding capabilities.

✨ Unique Features

  • Sovereign Digital Ego: A dynamic psychological profile (OCEAN traits) learned over time, used to personalize AI interactions without cloud tracking.
  • Tree of Thoughts (ToT) Reasoning: Parallel reasoning paths that are critiqued and synthesized for complex problem-solving.
  • Zero-Effort Identity: Automatically recognizes your name and adjusts its persona (Archivist, Scholar, Rebel, etc.) to match your mood.
  • Multimodal Ingestion: Seamlessly feeds on text, audio, images, and web clips.

🛠️ Technical Stack

  • Backend: FastAPI (Python), SQLAlchemy (SQLite), Alembic.
  • Intelligence: LangChain, Ollama (Local LLMs), Transformers, Sentence-Transformers.
  • Storage: ChromaDB (Vector), Neo4j/NetworkX (Graph).
  • Frontend: React (Vite), GSAP Animations, TanStack Query, Lucide Icons, Tailwind CSS.

🚀 Getting Started

Prerequisites

  • Python 3.10+
  • Node.js 18+
  • Ollama (running locally)

Installation

  1. Clone the Repository:

    git clone https://github.com/ipswyworld/akashic-records.git
    cd akashic-records
    
  2. Setup Backend:

    cd backend
    pip install -r requirements.txt
    cp .env.example .env
    alembic upgrade head
    python main.py
    
  3. Setup Akasha CLI (The Archivist's Interface):

    # From the project root
    pip install -e .
    
  4. Setup Frontend:

    cd frontend-react
    npm install
    npm run dev
    
  5. Setup Browser Extension:

    • Open Chrome/Edge.
    • Go to chrome://extensions/.
    • Enable Developer mode.
    • Click Load unpacked and select the browser-extension folder.

💻 CLI Usage

The akasha CLI allows you to interact with the Neural Core directly from your terminal.

  • Ask a question: akasha ask "What are my core research themes?"
  • Ingest a file: akasha ingest ./my_notes.txt
  • Visualize your Ego: akasha ego
  • Check system pulse: akasha pulse
  • Rename your Core: akasha rename "Jarvis"

🛡️ Security & Privacy

  • Local-First: All heavy lifting happens on your machine.
  • Encrypted Storage: Artifacts are encrypted before being stored in the database.
  • Sovereign Mode: A high-security tier that redacts PII and restricts external API calls.

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.


Akasha is not just a tool; it is a partnership. Welcome to your universal library.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

akashic_records_lib-0.1.4.tar.gz (83.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

akashic_records_lib-0.1.4-py3-none-any.whl (95.9 kB view details)

Uploaded Python 3

File details

Details for the file akashic_records_lib-0.1.4.tar.gz.

File metadata

  • Download URL: akashic_records_lib-0.1.4.tar.gz
  • Upload date:
  • Size: 83.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for akashic_records_lib-0.1.4.tar.gz
Algorithm Hash digest
SHA256 6e6fba1fb7b14ba4900ea36280dc320a02678b580b3c85858716689e35a6b455
MD5 a0385a5a40d936f745e7b96053485211
BLAKE2b-256 12d7d417dc8f1deb28fa91689c2d9128c504338cdcf4d492770ac5a5c833255f

See more details on using hashes here.

File details

Details for the file akashic_records_lib-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for akashic_records_lib-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 e56f42048e5310f0df7d2960db8f6fa61917c15418a0be850d1124da394a2232
MD5 48e49e784b8ee981a6cd94f217dbc3e6
BLAKE2b-256 8154a8754a56923ab09147f5b4aee1fb25a0b03c59234accf95ff478b42d7270

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page