Home / Open source / haystack

haystack

MCP client

deepset-ai/haystack · Enterprise stack · Enterprise

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over r

Verified via GitHub API

  • semantic-search
  • information-retrieval
  • ai
  • python
  • large-language-models
  • generative-ai
  • llm
  • rag
  • retrieval-augmented-generation
  • agents
  • orchestration
  • agent-framework
  • agentic-ai
  • agentic-rag
  • ai-agents
  • context-engineering
  • framework
  • genai
  • mcp
  • multi-agent

Data from GitHub API, refreshed Oct 17, 2026

Stars
26754
Forks
3297
License
Apache-2.0
Language
Python
Last commit
Oct 16, 2026
Latest release
v3.4.0
Release date
Oct 15, 2026
Contributors
508
Open issues
87
GitHub Project website

Works with — from README

MCP
MCP client
Models
Azure OpenAI, Bedrock, Mistral, OpenAI

Source: README.md keyword match (stated in README)

haystack FAQ

Is haystack free?

haystack is open source under the Apache-2.0 license. Hosted services and infrastructure may have separate costs.

How popular is haystack?

haystack has 26754 GitHub stars as of Oct 17, 2026.

Is there a hosted version of haystack?

A hosted alternative for haystack is unknown (—) in this data.

What does haystack work with?

From README: MCP client, Azure OpenAI, Bedrock, Mistral, OpenAI.