local-embeddings

Semantic search for Obsidian vaults using LanceDB and cloud or local embedding models

One brain. Every AI agent. Nothing forgotten. — Self-hosted memory layer via MCP + Postgres + pgvector

MCP RAG server — local embeddings, your docs never leave your machine. Private knowledge base + web search for Claude, Cursor, and Ollama. Drop your docs, connect your AI client, done.

A Python project that deploys a Local RAG chatbot using Ollama API. Refines answers with Deep Research from external websites, and uses both Embedding and LLM models.

Turn your voice into intelligent, linked notes inside Obsidian

Semantic code search for VS Code, powered by NightOwl-CodeEmbedding — my own ModernBERT Bi-Encoder trained from scratch. Codex/MCP ready!!

A Python project that deploys a Local RAG chatbot using Ollama API and vLLM API. Refines answers with internal RAG knowledge base, using both Embedding and Rerank models to improve accuracy of context provided to LLM models.

A Python project that deploys a Local RAG chatbot using Ollama API. Refines answers with internal RAG knowledge base, and uses both Embedding and LLM models.

Project-aware collection management based on Qdrant, including a Rust MCP, daemon and CLI: hybrid semantic, pattern and full-text (FTS5) search into single or cross-concerns collection. Dedicated collections for knowledge library, LLM behavioral rules, and an LLM scratchpad

MCP server that runs local LLMs (with full access to MCP tools included). Callable by Python to chain MCP tools with local intelligence.

A Fast API server that provides local text and multi-modal embedding using LlamaIndex Hugging Face Embedding

Local inference, memory-, chat- subsystem and AI agents

Memory-as-a-Service for AI Agents & LLMs. Add persistent memory, pgvector-based semantic search, and automatic semantic deduplication with 3 simple REST API endpoints. Comes with an LRU embedding cache and a developer analytics dashboard.

Intelligent enterprise knowledge platform that ingests Box content, transcribes audio/video with Whisper, indexes documents using ChromaDB and local embeddings, and answers questions with Amazon Bedrock Claude.

A lightweight Retrieval-Augmented Generation (RAG) agent powered by Groq AI and local embeddings, built to process and understand text data efficiently. It retrieves relevant context from your own files and generates accurate, natural-language responses -all while keeping your data private and running locally.

Offline Express.js QA API using Ollama. Parse PDFs, embed locally, search and chat with your private docs — no cloud needed.

Tiered semantic cache for LLMs — Redis exact-match + pluggable vector search (Chroma/Qdrant/Pinecone/pgvector) to avoid redundant LLM calls. FastAPI, production-hardened with request coalescing, circuit breaker, and Prometheus metrics.

RAG-powered Q&A assistant over 50 synthetic sales incentive plan documents - local ONNX embeddings (no PII leaves machine), ChromaDB retrieval, DeepSeek LLM via OpenRouter, RAGAS evaluation (faithfulness 0.745, relevancy 0.730), and Streamlit chat UI.

Two-project K-12 analytics suite for USD259 Wichita Public Schools - SQLite assessment pipeline with Streamlit dashboard, plus a FERPA-safe RAG chatbot over 60 synthetic district documents (ChromaDB, ONNX embeddings, RAGAS evaluation: context precision 0.970).

FastAPI | Postgres | Sentence Transformer | Local Embeddings saved to PGVector | JWT AUTH