🧠 AI second brain with reasoning, analysis & synthesis. Knowledge graphs, topic modeling, spaced repetition, automated reports. Real-time voice assistant, semantic search, smart plugins. Qdrant vectors + PostgreSQL + transformers. From conversations to connected intelligence - memory that thinks like you do.

A fully local RAG pipeline that answers natural language questions about movie reviews. Uses Ollama for embeddings + local LLM, Chroma for the vector store, and LangChain to retrieve, summarize, and generate answers.

Self-hosted RAG application for PDF question-answering using LangChain, ChromaDB, and Ollama. Features Flask web interface, vector embeddings, automated chunking, and local LLM inference. Includes CI/CD pipeline with automated testing.

A fully functional LLM chat backend with FastAPI and Async operations, with a built in MCTS conversation analyzer

Build production-ready backends in minutes

Vector Index Benchmark for Embeddings

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

The Identity layer for the agentic world

the AI-native open-source embedding database

A tiny GPT-style language model built from scratch. Built to explore ML internals and eventually expand to a browser-native tool.

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3

SharpAI

ASR model that uses audio frequencies instead of spectrograms. + pitch aware relative positional embeddings.

NLP

Java version of LangChain

A blazing fast inference solution for text embeddings models

The documentation repo for Weaviate Database, Cloud, Agents and much more!

A project to show howto use SpringAI with OpenAI to chat with the documents in a library. Documents are stored in a normal/vector database. The AI is used to create embeddings from documents that are stored in the vector database. The vector database is used to query for the nearest document. That document is used by the AI to generate the answer.

Find R packages matching either descriptions or other R packages