43 dependents
| Package | Description | Downloads/month |
|---|---|---|
| High-Performance Engine for Multi-Vector Search | 114K | |
| Anteroom - your gateway to AI conversation | 32K | |
| A local-first AI development environment powered by Claude Code | 8K | |
| search through files with fts5, vectors and get reranked results. Fast | 6K | |
| A claim-native database for building reality models | 4K | |
| System designed for embedding, indexing, and applying semantic search for person... | 4K | |
| svVascularize (svv): A synthetic vascular generation, modeling, and simulation p... | 4K | |
| Real-time neuro-/biosignal processing and streaming pipeline. | 3K | |
| svVascularize (svv): A synthetic vascular generation, modeling, and simulation p... | 2K | |
| Tooling for agile modeling on large machine perception embedding databases. | 2K | |
| Lightning Fast: Faiss CPU + Onnx Quantized Multilingual Embedding Model | 2K | |
| Async-first MongoDB-like persistence library with pluggable storage engines. | 2K | |
| Lightweight semantic code search engine — 2-stage vector + FTS + RRF fusion + MC... | 1K | |
| Tree-based visualization for high-dimensional data. Organizes similar items into... | 1K | |
| Agentic brain DB - the cognitive layer for AI agents | 1K | |
| Deterministic build-vs-borrow intelligence and open-source evaluation via MCP/CL... | 1K | |
| Dead-simple local vector database powered by usearch HNSW. | 1K | |
| The Agentic Memory Layer & Universal Retrieval Toolkit. Synthetic data generatio... | 1K | |
| Default template for PDM package | 944 | |
| Entity database for organizations, people, roles, and locations with embedding s... | 940 | |
| Simple EDM (Empirical Dynamic Modeling) library | 914 | |
| A pure Python-implemented, lightweight, server-optional, multi-end compatible, v... | 725 | |
| Where vectors come alive - A lightweight, visual-first vector database with embe... | 682 | |
| RAGoon : High level library for batched embeddings generation, blazingly-fast we... | 636 | |
| 571 | ||
| Local-first codebase intelligence with semantic search, multi-hop research, and ... | 511 | |
| ⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visua... | 265 | |
| Use LLM embeddings to create mappings between the Brick ontology and external vo... | 214 | |
| The AI-Native Database: JSON + Vectors + MCP | 213 | |
| A python project aimed at extracting embeddings from textual data and performing... | 180 | |
| Baguetter is a flexible and efficient search engine library implemented in Pytho... | 178 | |
| Persistent memory layer for LLM agents. Zero LLM calls, sub-100ms ingestion, det... | 144 | |
| MCP server for semantic document search with boundary-aware chunking | 143 | |
| flexible-semantic-kernel | 124 | |
| AI-assisted software development tool for streamlining development process | 120 | |
| Elemelek is designed to sample subsets of instructions gathered/generated from v... | 105 | |
| kiuk: Redefining how we remember in the new era. | 84 | |
| Arm MCP Server - Provides AI assistants with tools for Arm architecture developm... | 84 | |
| A hierarchical context management system for Large Language Models that acts as ... | 79 | |
| A programmable database that speaks Lua. Store data, run queries, build AI workf... | 69 | |
| PyDeevo is a comprehensive framework for neural network architecture search, hyp... | 59 | |
| Persistent memory layer for LLM agents. Zero LLM calls, sub-100ms ingestion, det... | 43 | |
| The AI-Native Database: JSON + Vectors + MCP | 1 |
