vector-database

visualization tool for vector search index

GraphRAG over any codebase — a Neo4j knowledge graph of code entities plus a 3072-dim vector index, bridged so one natural-language query walks structure and ranks by meaning. Python · Neo4j · OpenAI embeddings · Streamlit · Docker. Hybrid semantic + structural code search.

Our powerful image search engine uses vector databases to store and search for similar images. Upload your images and use an input image to quickly identify the closest matches. With our app, you can easily organize and search your image collection with speed and accuracy. Try it today!

Embedded database for agentic memory — relational, graph, and vector under unified MVCC transactions

Optimizing bit-level Jaccard Index and Population Counts for large-scale quantized Vector Search via Harley-Seal CSA and Lookup Tables

Exploring the Basics of Langchain

An open source framework for Retrieval-Augmented System (RAG) uses semantic search helps to retrieve the expected results and generate human readable conversational response with the help of LLM (Large Language Model).

ContextQA - The open-source tool for data-driven conversations

Training-free ordinal & sign quantization for compressed nearest-neighbour retrieval over high-dimensional embeddings. Pure Rust, zero system dependencies.

⚠️ DEPRECATED - Use https://github.com/SylphxAI/coderag instead

A modular framework for building and deploying Retrieval-Augmented Generation (RAG) systems with built-in evaluation and monitoring.

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

An open-source vector database

Memcortex is a lightweight semantic memory layer for LLMs using open source embedding model and Weaviate for vector storage and retrieval.

A better version of KU's course catalogue

High-performance, Hardware-First Vector Database engine built in Zig and Go. Sub-millisecond HNSW search with 64-bit metadata filtering and 1.8MB binary footprint.

Chat with Anything 📃

🧬 Self-optimizing vector database using MAP-Elites. 51x faster than ChromaDB, 82x faster than LanceDB, 100% recall. Auto-evolves optimal index configs via Quality Diversity.

Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS.

NewsPulse is AI powered news analytics app for investors