haystack

Haxall IoT framework

Automate Hay Day farming with Hay Star, a native ultra-fast bot featuring anti-ban spoofing and autonomous supervision.

OpenTelemetry Instrumentation for AI Observability

Easily deploy Haystack pipelines as REST APIs and MCP Tools.

🛠️ Build powerful search systems effortlessly with Haystack, a framework for developing end-to-end question answering and search applications.

Build AI agents in Django. Batteries included.

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack

Production-ready Haystack/LangChain pipelines for Hybrid & Parent-Child Retrieval, Diversity Filtering, MMR, Metadata Filtering, Reranking, Query Enhancement, Multi-Tenancy, Agentic RAG across Pinecone, Weaviate, Milvus, Qdrant, Chroma with dataset loaders, evaluation tooling, and benchmarks for TriviaQA, ARC, PopQA, FactScore and Earnings Calls.

Transcribe and summarize any YouTube video instantly with AI-powered app using Whisper, Gemini, Streamlit, yt-dlp & FFmpeg.

Agentic RAG, Off Grid — a self-hosted RAG MCP server for OpenWebUI

Institutional memory for the agentic era. Open-source GraphRAG knowledge base: documents in, Neo4j knowledge graph out. Humans get chat + deep research with cited answers, agents get a 100+ endpoint REST API, plug-in apps run right inside the instance. Self-host with one command: npx @mocaos/cortex

Haystack components for SayMaker: generate images and video in a pipeline

Runnable examples for the Pink Agentic AI Payments sandbox: MCP + REST, test credentials, no money moves.

Here you can find all the Tutorials for Haystack 📓

Haystack component for YouTube transcripts as Documents (GetYouTubeTranscript API)

RAG frameworks benchmark (Oct 2026): LangChain, LlamaIndex, Haystack, DSPy vs plain Python on one scraped docs corpus, plus LightRAG and GraphRAG

Multi-agent research assistant: planner/researcher/summarizer/critic/writer agents over hybrid retrieval (LlamaIndex + Haystack + ChromaDB + Redis + FastAPI)

Phone approvals for Haystack agents. Your agent asks, your user taps Approve or Deny.

Telegram assistant with per-user vector memory and source-cited document RAG using Haystack, Pinecone and Docling.

Telegram group discussion assistant with session-scoped capture, Pinecone persistence, strict isolation and fail-closed whole-session summaries.