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. observed · 2026-08-28
Health v2 · maintenance only
99/100
- Activity 99
- Release rhythm 99
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: 12
- age_days: 2484
- days_rel: 9
- days_push: 7
- n_releases_24m: 56
Adoption not part of the score
26325 stars · 3042 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Haystack is an open-source Python AI orchestration framework by deepset for building production-ready LLM applications, agents, and RAG systems using composable pipelines. It offers modular components for retrieval, memory, routing, and generation, with 180+ integrations across model providers, vector databases, and monitoring tools.
Use cases
- build a RAG pipeline over my own documents
- create AI agents that use tools and memory
- build semantic search over a document collection
- orchestrate multi-step LLM workflows in production
- build a chatbot that answers questions from a knowledge base
- connect OpenAI or Anthropic models to a vector database
- build multimodal LLM applications
- prototype and deploy agentic AI systems
When to choose
- you need a mature, production-tested framework for RAG or agent pipelines
- you want explicit control and visibility over retrieval, routing, and generation steps
- you need vendor-neutral integrations with many LLM providers and vector stores
- you want serializable, Kubernetes-ready pipelines for enterprise deployment
When to avoid
- you only need a thin wrapper around one LLM API for simple calls
- you prefer a minimal single-file agent loop over a structured pipeline framework
- you need a no-code or fully managed platform rather than a Python framework
Facets
framework · maturity stable
agent-framework rag llm-inference search-engine vector-database chatbot workflow-automation mcp prompt-engineering artificial-intelligence large-language-models machine-learning developer-tools python cross-platform cloud self-hosted llm-orchestration pipelines semantic-search context-engineering multi-agent document-stores generative-ai production-ai ai-agents retrieval-augmented-generation search natural-language-processing docker kubernetes
6 sources
- readme: https://github.com/deepset-ai/haystack · fetched 2026-08-28 · 513eac950aea
- homepage: https://haystack.deepset.ai · fetched 2026-08-29 · 9a84f1bc0bab
- site_page: https://docs.haystack.deepset.ai/docs · fetched 2026-08-29 · 44136fa355b3
- site_page: https://docs.haystack.deepset.ai/docs/intro · fetched 2026-08-29 · c65444430e96
- site_page: https://www.deepset.ai/about · fetched 2026-08-29 · 32b51e5e3c49
- site_page: https://haystack.deepset.ai/integrations · fetched 2026-08-29 · 20a0ff4e5eaf
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| deepset-ai/haystack | main | 99 |
For agents
markdown · JSON · MCP: product_card(name="deepset-ai/haystack")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem