BigHugger
GH Repository · deepset-ai

haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

stars
26,512
30-day movement
+4314/day
Related entries
60
Connections
3
Pythonmulti-agentmcpframeworkcontext-engineeringai-agentssemantic-searchinformation-retrievalaillmpythongenailarge-language-modelsgenerative-airagretrieval-augmented-generationagentsorchestrationagentic-ragagentic-aiagent-framework

Haystack is an open-source Python orchestration framework for building LLM applications. It lets you compose modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation.

Reach for it when you need structured, production-oriented pipelines for RAG, agents, or semantic search rather than ad-hoc LLM glue code.

Use it to

  • Build retrieval-augmented generation pipelines
  • Create multi-agent workflows
  • Implement semantic search over your data
  • Build conversational systems with memory
  • Compose multimodal LLM applications

For Python developers building production LLM and RAG applications

Role
rag
Language
Python
Licence
Apache-2.0
Forks
3,137
Open issues
80
Last push
2026-09-15
Latest release
0.1.0 · 2019-11-28
topicsragorchestrationagentssemantic-searchllmpython