Open-source AI memory and evolution system
Project description
๐ง Jema AI Core (formerly Athena Brain Core)
Give your AI a brain that remembers and evolves
Powered by Jema AI - ํ์์ ์ฐจํธ๋ณด์กฐ AI์ ์คํ์์ค ๊ธฐ์ ์คํ
๐ Jema AI ์ฒดํํ๊ธฐ (B2B ํ์์ ์๋ฃจ์ ) | ๐ Persona Diary ๋ค์ด๋ก๋ (B2C ์ฑ)
๐ฏ What is Jema AI Core?
Jema AI Core (formerly Athena Brain Core) solves the fundamental limitations of large language models:
- โ No long-term memory - ChatGPT forgets everything after each conversation
- โ No personalization - Same answers for everyone
- โ No evolution - Repeats the same mistakes
Jema AI Core gives any AI:
- ๐ง Long-term memory - Remembers everything, maintains project context
- ๐ Self-evolution - Learns from mistakes, auto-generates rules
- ๐ค True personalization - Understands your style, learns your preferences
- ๐ Privacy-first - 100% local storage, your data stays on your computer
๐ Quick Start
Installation
# Clone the repository
git clone https://github.com/mkmlab-hq/athena-brain-core.git
cd athena-brain-core
# Install dependencies
pip install -r requirements.txt
# Initialize Athena Brain
python -m athena_brain init
Basic Usage
from athena_brain import AthenaBrain
# Initialize
brain = AthenaBrain()
# Store a memory
brain.store_memory(
content="User prefers Python over JavaScript",
category="preference"
)
# Search memories
results = brain.search_memory(
query="What programming language does the user prefer?",
limit=5
)
# Auto-evolution: Track mistakes and learn
brain.track_mistake(
pattern="validation_error",
solution="Always validate input before processing"
)
โจ Core Features
1. Long-term Memory (Local Qdrant)
- Automatic conversation storage - Every chat is saved
- Semantic search - Find relevant memories instantly
- Project context - Maintains context across sessions
- 100% local - Your data never leaves your computer
2. Self-Evolution
- Mistake pattern tracking - Automatically detects repeated errors
- Rule auto-generation - Creates rules from mistakes
- Continuous improvement - Gets smarter every day
3. Personalization
- Style learning - Learns your coding style, preferences
- Constitution-based analysis (MKM12) - Understands your personality
- Adaptive responses - Tailored to you
4. Privacy-First
- Local storage - All data on your PC
- Encryption - AES-128-CBC + HMAC-SHA256
- No cloud required - Works completely offline
๐ Performance Improvements (2025-11-27)
Latest Performance Benchmarks
- โ Response Time: 75-80% reduction (8-12s โ 1.5-2.5s)
- โ Token Consumption: 97.9% savings (13,869 โ 295 tokens)
- โ Rules Optimization: 96% reduction (73 โ 3 files)
- โ First Response Time: 85-90% reduction (5-8s โ 0.5-1s)
- โ Long-term Memory Search: 50% faster (800-1200ms โ 400-600ms)
Optimization Factors
-
Rules Optimization (40-50% contribution)
- Duplicate rules removed
- alwaysApply rules minimized (67 โ 3)
- Priority reorganized
-
VPS Swap Optimization (30-40% contribution)
- Swappiness: 60 โ 10
- RAM utilization: 2.25x improvement
- Disk I/O: 80% reduction
-
MCP Server Python Unification (10-20% contribution)
- NPX servers removed
- Environment consistency achieved
- Server response time: 40% faster
Advanced Features
- โ Long-term Memory Fusion Reasoning: 6 collections simultaneous search
- โ Web Search Auto-Detection: Cost-optimized (Ollama first)
- โ Intelligent Metacognition: Pattern recognition, emotional tagging, neural network expansion
- โ Qdrant Status: 7 collections, HTTP 200 (normal operation)
๐๏ธ Architecture
Jema AI Core
โโโ Local Memory (Qdrant)
โ โโโ Conversation storage
โ โโโ Semantic search
โ โโโ Vector embeddings
โโโ Self-Evolution Engine
โ โโโ Mistake tracking
โ โโโ Rule generation
โ โโโ Continuous learning
โโโ Personalization Engine
โ โโโ Style learning
โ โโโ Preference tracking
โ โโโ Adaptive responses
โโโ AI Integration
โโโ ChatGPT API
โโโ Claude API
โโโ Gemini API
โโโ Cursor (MCP)
๐ข MKM Lab ์ ํ๊ตฐ
Jema AI Core (์คํ์์ค) โ ํ์ฌ ํ๋ก์ ํธ
Jema AI (B2B ํ์์ ์๋ฃจ์
) โ ์ฃผ ์์ต
Persona Diary (B2C ์ฑ) โ ๋ณด์กฐ ์์ต
A-CodeAI (๊ฐ๋ฐ์ ํฌํธ) โ Phase 3
๐ข ๊ด๋ จ ์ ํ
1. Jema AI (B2B ํ์์ ์๋ฃจ์ ) โญ ์ฃผ ์์ต
"Jema AI Core ๊ธฐ์ ์ ํ์ฉํ ํ์์ ์ฐจํธ๋ณด์กฐ AI"
- ๐ฅ ํ๊ฒ: ํ์์ ์์ฅ, ํ์์ฌ
- ๐ฐ ๊ฐ๊ฒฉ: ์ ๊ตฌ๋ ๋๋ ๋ผ์ด์ ์ค
- ๐ฏ ๊ธฐ๋ฅ: ์ฐจํธ๋ณด์กฐ, ์ฒด์ง ๋ถ์, ๋ง์ถคํ ์ถ์ฒ
- ๐ ์ฌ์ดํธ: jema-ai.com
๐ Jema AI ์ฒดํํ๊ธฐ (B2B ์์ ๋ฌธ์)
2. Persona Diary (B2C ์ฑ) โญ ๋ณด์กฐ
"๋๋ง์ AI ๋๋ฐ์ - ์ ์ฌ ์ถ์ฒ, ์๋ ์ผ๊ธฐ"
- ๐ฑ ํ๊ฒ: ์ผ๋ฐ ์ฌ์ฉ์
- ๐ฐ ๊ฐ๊ฒฉ: ๋ฌด๋ฃ (ํ๋ฆฌ๋ฏธ์ ๊ตฌ๋ ๊ฐ๋ฅ)
- ๐ฏ ๊ธฐ๋ฅ: ์ ์ฌ ์ถ์ฒ, ์๋ ์ผ๊ธฐ, ์ฒด์ง ๊ธฐ๋ฐ ๋ง์ถคํ ์ถ์ฒ
- ๐ ์ฌ์ดํธ: personadiary.com
๐ Persona Diary ๋ค์ด๋ก๋ (B2C ์ฑ)
3. A-CodeAI Developer Portal (Phase 3, ์กฐ๊ฑด๋ถ)
"Jema AI Core ๊ธฐ์ ์ API ๋ฐ ๊ฐ๋ฐ์ ํฌํธ"
- ๐จโ๐ป ํ๊ฒ: ๊ฐ๋ฐ์, AI ์ฐ๊ตฌ์
- ๐ฐ ๊ฐ๊ฒฉ: API ํธ์ถ๋ฃ ๋๋ ๊ตฌ๋
- ๐ฏ ๊ธฐ๋ฅ: Athena API, Jema API, ๊ฐ๋ฐ์ ๋๊ตฌ
- ๐ ์ฌ์ดํธ: a-codeai.com
๐ A-CodeAI Developer Portal (Coming Soon 2026)
๐ Latest Features (2025)
- โ Agentic RAG: Intelligent query routing with LLM Router (Adaptive RAG)
- โ GraphRAG: Knowledge graph-based search for domain expertise
- โ CRAG: Corrective RAG for quality assurance and automatic fallback
- โ Pattern Recognition: FAST/MEDIUM/DEEP adaptive analysis paths
- โ Emotion Tagging: 5 emotion types (satisfaction, frustration, surprise, confusion, pride)
- โ Neural Network Expansion: Automatic memory connection creation and strengthening
- โ MCP Integration: 15+ MCP servers for enhanced AI capabilities
- โ Large-Scale Data Integration: Genesis Mission-style data integration platform (GitHub, web search, user feedback)
๐ Requirements
- Python 3.11+
- Qdrant (local or VPS)
- 4GB RAM minimum
- 10GB disk space
๐ง Configuration
Create .athena/config.yaml:
memory:
qdrant_url: "http://localhost:6333"
collection_name: "athena_memories"
evolution:
auto_track: true
rule_threshold: 2
personalization:
enable_mkm12: true
learning_rate: 0.1
๐ฏ Use Cases
For Developers
- Project context - AI remembers your entire project
- Code style - Learns your coding preferences
- Mistake prevention - Auto-generates rules from errors
For Content Creators
- Writing style - Learns your voice and tone
- Topic memory - Remembers what you've written about
- Preference learning - Adapts to your needs
For Everyone
- Personal AI - Truly understands you
- Privacy - Your data stays local
- Evolution - Gets smarter over time
๐ A-CodeAI Developer Portal
์ด ์คํ์์ค๋ **A-CodeAI Developer Portal**์ ์ผ๋ถ์ ๋๋ค.
์ ํ ์๊ฐ
A-CodeAI๋ "Self-Evolving Systems๋ฅผ ๋ง๋๋ ์์ง๋์ด๋ง ํ๋ซํผ"์ ๋๋ค:
- Athena Workspace AI: ์๋ ํ์ผ ์ ๋ฆฌ, ํ๋ก์ ํธ ๊ด๋ฆฌ
- Athena Search API: ์น + ๋๋ฉ์ธ ์ง์ RAG ๊ฒ์
- Athena Unified RAG: ํตํฉ RAG ์์ง (์น + ์ฝ๋ + ๋ฉ๋ชจ๋ฆฌ)
- Dynamic Rules Engine: ์ค์ ์๋ ๋ฐฉ์ง, Rules ์๋ ์์ฑ
- A-CODE Core: 12์ฐจ์ ์ํ ์์ง (Enterprise)
- ์ฅ๊ธฐ๊ธฐ์ต ์์คํ : ์ด ๋ ํฌ์งํ ๋ฆฌ (Jema AI Core)
๋ฌด๋ฃ๋ก ์์ํ๊ธฐ
- Developer Portal ๋ฐฉ๋ฌธ
- Free Tier API Key ๋ฐ๊ธ
- ๋ฌธ์ ์ฐธ๊ณ
์์ ์ ์ฌ์ฉ
- Pro/Enterprise: ๊ฐ๊ฒฉ ์ ์ฑ
- Jema API: jema-ai.com (B2B ํ์์ ์๋ฃจ์ )
- Athena API: a-codeai.com/api (์์จ์ฑ์ฅ ๊ธฐ์ต API)
๊ด๋ จ ๋ ํฌ์งํ ๋ฆฌ
- cursor-advanced-rules - Cursor Rules ์ต์ ํ
- athena-mcp-servers - MCP ์๋ฒ ๊ตฌํ
- mkm12-core-engine - MKM12 ์ฝ์ด ์์ง
- icd-unified-model - ICD ํตํฉ ๋ชจ๋ธ
๐ Part of Athena Ecosystem
- Athena MCP Servers - Essential MCP servers for Cursor IDE
- Cursor Advanced Rules - Optimized Cursor Rules system (6 essential rules)
- MKM12 Core Engine - Constitutional analysis engine
- ICD Unified Model - Causal AI framework
- A-Code AI - Developer portal for Jema API & Athena API
- MKM Life - Integrated health platform (Showroom + B2C)
- Persona Diary - AI-powered diary generation with emotion analysis
๐ค Contributing
We welcome contributions! Please see CONTRIBUTING.md for details.
Development Setup
# Clone and setup
git clone https://github.com/mkmlab-hq/athena-brain-core.git
cd athena-brain-core
pip install -r requirements-dev.txt
# Run tests
pytest
# Run linter
black .
flake8 .
๐ Roadmap
- Core memory system (Qdrant)
- Self-evolution engine
- Basic personalization
- Web dashboard
- Cloud sync (optional)
- Team collaboration
- Enterprise features
๐ฐ Pricing
Athena Brain Core: Free forever (Open Source, MIT License)
Commercial Products:
- Jema AI (B2B): Monthly subscription or license - Learn More
- Persona Diary (B2C): Free with premium options - Learn More
๐ Privacy & Security
- 100% Local - All data stored on your computer
- Encryption - AES-128-CBC + HMAC-SHA256
- No Tracking - We don't track you
- Open Source - Fully auditable
Security Policy: See SECURITY.md for reporting vulnerabilities.
๐ Documentation
- Full Documentation
- API Reference
- Examples
- Athena API Documentation - Cloud API service
- Jema API Documentation - Korean medicine intelligence API
๐ Support
- ๐ฅ B2B ์์ ๋ฌธ์: jema-ai.com (Jema AI - ํ์์ ์๋ฃจ์ )
- ๐ฑ B2C ์ฑ: personadiary.com (Persona Diary)
- ๐จโ๐ป ๊ฐ๋ฐ์ ํฌํธ: a-codeai.com (Coming Soon 2026)
- ๐ Issues: GitHub Issues
- ๐ฌ Discussions: GitHub Discussions
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
โข๏ธ Trademark Notice
Registered Trademarks:
- "MKM Lab" ยฎ - Registered trademark of MKM Lab
- "Persona Diary" ยฎ - Registered trademark of MKM Lab
Trademarks (In Use):
- "Athena Brain", "Athena API", "Jema API", "MKM Life", "A-Code AI" are trademarks of MKM Lab. All rights reserved.
Important: This license does not grant permission to use the trade names, trademarks, service marks, or product names of MKM Lab, except as required for reasonable and customary use in describing the origin of the Work.
๐ Acknowledgments
- Built with Qdrant for vector storage
- Powered by sentence-transformers for embeddings
- Inspired by the need for AI that truly understands you
โญ Star Us!
If you find Athena Brain useful, please star this repository! It helps us grow the community.
Made with โค๏ธ by MKM Lab
Part of the MKM Life AI Ecosystem
ยฉ 2025 MKM Lab. All rights reserved.
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 athena_brain_core-0.1.0.tar.gz.
File metadata
- Download URL: athena_brain_core-0.1.0.tar.gz
- Upload date:
- Size: 9.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4fdb634aa55d7aae220c8c8a97a07ef19e9e5ff56af44ed959a317c78abee726
|
|
| MD5 |
67c25fda09a0db78610b483cf3f70715
|
|
| BLAKE2b-256 |
c50648d733b9c7e742f6f040453334d5e739fd984199fd3d3d637d21fd20c969
|
File details
Details for the file athena_brain_core-0.1.0-py3-none-any.whl.
File metadata
- Download URL: athena_brain_core-0.1.0-py3-none-any.whl
- Upload date:
- Size: 9.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d9c2da08851c815381b08fe40c599d39965606755bd9b02d80c2f0810a600d63
|
|
| MD5 |
a1708f1423db3ab9048ab8f48910c417
|
|
| BLAKE2b-256 |
61d4606ebb1313a3933cbd0f6936f73fcb14f86a576cd2945d657714b1cba749
|