Skip to content
View MrDewitt88's full-sized avatar
😎
😎

Block or report MrDewitt88

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MrDewitt88/README.md

πŸ‘‹ Hi, I'm Alexander

πŸš€ Building the first MLX UnifiedDB for Enterprise AI

Currently developing db_core - the world's first enterprise AI database with native MLX integration for Apple Silicon.

πŸ† Performance Achievements

  • 37% faster than Pinecone for vector search
  • 11x faster than Neo4j for graph operations
  • 76% energy savings vs GPU-based solutions
  • 3,320 ops/s bulk document processing on Apple Silicon

πŸ› οΈ Tech Stack

πŸ”₯ Core: MLX β€’ Apple Silicon β€’ Python β€’ Swift πŸ—„οΈ Databases: VectorDB β€’ GraphDB β€’ Knowledge Graphs 🧠 AI/ML: Neural Networks β€’ Logic Tensor Networks β€’ Causal Inference πŸ—οΈ Architecture: Multi-Tenant β€’ Unified Memory β€’ Zero-ETL ⚑ Performance: Apple Neural Engine β€’ MLX Optimization

🎯 Current Focus

  • πŸ”¬ MLX Ecosystem Pioneer: Contributing to commercial MLX development
  • 🏒 Enterprise AI: Building production-ready UnifiedDB for Apple Silicon
  • πŸ‡¦πŸ‡Ή Austrian Deep Tech: AWS PreSeed Deep Tech applicant
  • 🌍 Open Source: Contributing MLX database primitives to community

πŸ“Š Latest Benchmarks

Operation db_core (MLX) Competition Advantage
Vector Search 823 ops/s 400-600 ops/s +37-106%
Graph Traversal 1,668 ops/s 150 ops/s +1,012%
Neural Embeddings 16,575 ops/s 2,000 ops/s +729%
Memory Efficiency 2.7 MB/1k docs 4-6 MB/1k docs +48-122%

πŸ”— Connect & Collaborate

πŸ“ˆ GitHub Stats

GitHub stats

πŸ† Featured Projects

⭐ Check out my pinned repositories for MLX database innovations!


πŸ’‘ "Making Apple Silicon the future of Enterprise AI, one MLX optimization at a time."

Popular repositories Loading

  1. MrDewitt88 MrDewitt88 Public

    Config files for my GitHub profile.

  2. mlx-lm mlx-lm Public

    Forked from ml-explore/mlx-lm

    Run LLMs with MLX

    Python

  3. mlx mlx Public

    Forked from ml-explore/mlx

    MLX: An array framework for Apple silicon

    C++

  4. mlx-data mlx-data Public

    Forked from ml-explore/mlx-data

    Efficient framework-agnostic data loading

    C++

  5. mlx-vlm mlx-vlm Public

    Forked from Blaizzy/mlx-vlm

    MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

    Python

  6. mlx-embeddings mlx-embeddings Public

    Forked from Blaizzy/mlx-embeddings

    MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

    Python