Category
Data & ETL
Connectors, pipelines, vector stores.
24 listings
Every Data & ETL listing on ai-supply is a free, open-source AI capability that we scan and grade A–D for security before it appears here — so you can adopt with confidence, not just a star count. This category spans 16 Connectors, 4 MCP servers, 2 Pipelines, 1 Eval and 1 Dataset.
Security posture: 8 of 24 scanned rated safe · avg score 84/100.
⇄موصّل
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
ai-supply
✓ A · 95⟳ 29d agoshellnetworkfs
↓ 811k
⇄موصّل
DuckDB
In-process OLAP SQL database that runs inside your Python, R, or Node.js process — no server required.
ai-supply
✓ A · 100⟳ 1mo agonetworkfs
↓ 597k
⇄موصّل
Polars
Blazing-fast DataFrame library written in Rust with a Python API — handles datasets that don't fit in RAM.
ai-supply
! B · 75⟳ 16d agoshellnetworkfs
↓ 346k
⇄موصّل
pgvector
Open-source vector similarity search for PostgreSQL — store and query embeddings directly in your Postgres DB.
ai-supply
✓ A · 100⟳ 22d agonetwork
↓ 337k
⇄موصّل
Milvus
Cloud-native open-source vector database built for billion-scale similarity search and AI applications.
ai-supply
! B · 75⟳ 1mo agoinstall-hooknetworkfs
↓ 236k
⇄موصّل
Weaviate
Open-source vector database with hybrid search, multi-tenancy, and native ML module integrations.
ai-supply
! B · 88⟳ 16d agonetwork
↓ 206k
△تقييم
Great Expectations
Data quality framework for defining, testing, and documenting expectations about your data pipelines.
ai-supply
! B · 75⟳ 11d agoguards:2
↓ 185k
⬡مسار
dlt (data load tool)
Open-source Python library for building self-maintaining, schema-evolving data pipelines with minimal code.
ai-supply
! B · 75⟳ 1mo agosecretsshellinstall-hook
↓ 164k
⇄موصّل
LlamaIndex
The leading data framework for LLM apps — 150+ data loaders, RAG pipelines, and agent tools for connecting any data source to any model.
ai-supply
✓ A · 100⟳ 23d agofs
↓ 156k
⇄موصّل
MarkItDown
Microsoft's universal document-to-Markdown converter: PDF, DOCX, PPTX, XLSX, HTML, images, audio, and ZIP — all to clean Markdown.
ai-supply
✓ A · 100⟳ 1mo agoshellnetworkfs
↓ 143k
▣مجموعة بيانات
Deep Lake
AI data lake with multimodal tensor storage, vector search, and serverless SQL — stream datasets directly to PyTorch and TensorFlow.
ai-supply
✓ A · 100⟳ 7mo agoPII
↓ 129k
⇄موصّل
Chroma
The open-source AI-native vector database — store, query, and filter embeddings with a simple Python API. Perfect for RAG and semantic search.
ai-supply
! B · 75⟳ 4mo agoshellinstall-hooknetwork
↓ 127k
⇄موصّل
LanceDB
Serverless, embedded vector database built on Lance columnar format — zero-copy, multimodal, no server needed.
ai-supply
! B · 88⟳ 11d agoshellnetworkfs
↓ 105k
⇄موصّل
Qdrant
High-performance vector database with filtering, payload storage, and a REST/gRPC API — built for production AI.
ai-supply
✓ A · 95⟳ 7d agonetwork
↓ 103k
⇄موصّل
Unstructured
Open-source document ingestion library — partition PDFs, HTML, DOCX, and 25+ formats into clean elements for RAG pipelines.
ai-supply
! B · 75⟳ 14d agoshellinstall-hooknetwork
↓ 72k
◇خادم MCP
Supabase MCP Server
Connect Supabase projects to AI assistants to manage tables, fetch config, and query Postgres data.
ai-supply
! B · 75⟳ 7d agoshellnetworkfs
↓ 51k
⇄موصّل
Crawl4AI
LLM-friendly open-source web crawler that turns pages into clean Markdown/JSON ready for RAG and agent pipelines.
ai-supply
! B · 75⟳ 11d agoshellnetworkfs
↓ 42k
◇خادم MCP
Qdrant MCP Server
Official Qdrant MCP server — a semantic memory layer for storing and retrieving vectors.
ai-supply
! B · 75⟳ 9mo ago
↓ 41k
⇄موصّل
DuckDB & MotherDuck MCP Server
Local MCP server that lets agents run analytical SQL over DuckDB files and MotherDuck cloud warehouses.
ai-supply
! B · 88⟳ 23d agoshellnetworkfs
↓ 34k
⬡مسار
Chonkie
Lightweight, fast text-chunking library purpose-built for RAG ingestion, with token, sentence, semantic, and code-aware chunkers.
ai-supply
! B · 75⟳ 2mo agosecretsnetworkfs
↓ 31k
◇خادم MCP
Neo4j MCP Servers
Neo4j Labs MCP servers for Cypher queries, knowledge-graph memory, and Aura instance management.
ai-supply
! B · 75⟳ 5mo agoshellnetworkfs
↓ 9.7k
◇خادم MCP
ClickHouse MCP Server
Official ClickHouse MCP server — run read-safe SQL and explore databases and tables.
ai-supply
✓ A · 95⟳ 8d agoshellnetworkfs
↓ 2.2k
⇄موصّل
Postgres MCP Pro
MCP server giving agents safe PostgreSQL access plus index tuning, execution-plan analysis, and database health checks.
ai-supply
! B · 75⟳ 1y agonetworkfs
↓ 1.3k
⇄موصّل
MongoDB MCP Server
Official MCP server connecting agents to MongoDB databases and Atlas clusters for queries, aggregation, and admin.
ai-supply
! B · 75⟳ 8d agoshellnetworkfs
↓ 992