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.

95
/ 100
Verified

Designed around a DAG-based pipeline architecture with first-class support for tool calling and function composition, Haystack integrates vendor-agnostic with OpenAI, Anthropic, Cohere, Hugging Face, AWS Bedrock, and local models. Built-in components handle retrieval, indexing, memory, and evaluation, while the extensible component interface enables custom operators and third-party integrations through Hayhooks for REST API and MCP server deployment.

24,487 stars and 671,835 monthly downloads. Used by 10 other packages. Actively maintained with 188 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

24,487

Forks

2,650

Language

MDX

License

Apache-2.0

Last pushed

Mar 12, 2026

Monthly downloads

671,835

Commits (30d)

188

Dependencies

18

Reverse dependents

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/deepset-ai/haystack"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.