[opensourcedex]

haystack is a free, open source orchestration & scheduling project written in Python and released under Apache-2.0. It has 26,913 GitHub stars, 3,384 forks and 143 open issues, and was last pushed 16 hours ago. On this registry it ranks #7 of 130 tracked projects in Orchestration & Scheduling, with 5 head-to-head comparisons available. It gained 281 stars over the last 30 tracked days.

What is haystack?

Haystack is an open-source AI orchestration framework written in Python under the Apache-2.0 licence, for building context-engineered, production-ready large language model applications as modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation, and it is aimed at developers and teams building scalable agents, retrieval-augmented generation, multimodal applications, semantic search, question answering, and conversational systems.

What it is

Haystack is a Python framework for orchestrating large language model applications, maintained by deepset and distributed as the package haystack-ai. It lives in the Python LLM application ecosystem, occupying the orchestration layer between a model provider and a finished application: the part that decides what to retrieve, where to route a query, what to keep in memory, and how to generate a response. The project is at version 3.0, and the repository carries roughly 26,530 stars, 3,143 forks, and 143 open issues. Documentation is hosted at docs.haystack.deepset.ai, with project information at haystack.deepset.ai and a release announcement at haystack.deepset.ai/blog/haystack-3-release.

The concrete problem it solves is orchestration written by hand. Instead of wiring retrieval, routing, memory, and generation together as bespoke glue code for every application, Haystack expresses those steps as modular pipelines and agent workflows with explicit control over each stage. The README describes a transparent architecture that lets teams experiment, customize deeply, and deploy with confidence, and the same building blocks serve both straightforward RAG systems and autonomous agents.

Key capabilities

  • Modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation.
  • Retrieval-augmented generation, including agentic RAG, reflected in the topic list entries agentic-rag and information-retrieval.
  • Autonomous agents and agent frameworks, reflected in topics such as agent-framework, agents, and ai-agents.
  • Multimodal applications, semantic search, question answering, and conversational systems built from the same architecture.
  • Context engineering treated as a first-class concern, alongside generative AI and large language models in the topic list.
  • Distribution as haystack-ai on PyPI and on conda-forge, with nightly pre-releases available through pip install --pre haystack-ai.
  • Installation paths beyond pip, including Docker images, documented in the README installation section.

Who uses it and how

  • Development teams building RAG, semantic search, question answering, or conversational applications in Python, using pipelines as the unit of composition.
  • Teams building autonomous agents and agentic RAG workflows, where routing and memory require explicit, inspectable control.
  • Organizations listed in the README's "Organizations using Haystack" section, indicating production adoption beyond individual projects.
  • Enterprises wanting vendor backing: the README includes a "Haystack Enterprise: Support & Platform" section, a commercial offering alongside the open-source framework.
  • Contributors and users coordinating through the project Discord and the haystack_ai account on Twitter, with 143 open issues on the tracker.

Getting started

Install from PyPI with pip install haystack-ai; the same package is available from conda-forge, and Docker images are documented in the README. Nightly pre-releases install with pip install --pre haystack-ai.

How it compares

No list of paid products that Haystack replaces is supplied in the available facts, and no comparable orchestration frameworks are named either. On the evidence here it stands alone in this registry; the only commercial counterpart mentioned is the maintainers' own "Haystack Enterprise: Support & Platform" section, presented as support and platform around the open-source framework rather than as a replacement for it.

When to use it — and when not to

Choose Haystack when orchestration must be explicit and inspectable and the team is comfortable operating a Python application; nothing in the facts gives it a database, storage, or SMTP dependency, so operational weight sits in the surrounding application. Check the README's Telemetry section before deployment if outbound reporting matters, and note that enterprise support and platform is a separate commercial path. Teams wanting a fully managed, no-code service, or not working in Python, should look elsewhere, and because the README excerpt is largely badges and installation instructions, docs.haystack.deepset.ai rather than the repository page is the practical source of truth.

project readme (upstream, from github) — read inline

Blue banner with the Haystack logo and the text ‘haystack by deepset – The Open Source AI Framework for Production Ready RAG & Agents’ surrounded by abstract icons representing search, documents, agents, pipelines, and cloud systems.
CI/CD Tests types - Mypy Coverage badge Ruff
Docs Website
Package PyPI PyPI - Downloads PyPI - Python Version Conda Version GitHub License Compliance HVTrust Evidence Grade OpenSSF Best Practices
Meta Discord Twitter Follow

🎉🎊✨   Haystack 3.0 is out!   ✨🎊🎉

Read the announcement here!

🥳 🎈 🎆 🪅 🎇 🍾 🥂 🎁 🌈

Haystack is an open-source AI orchestration framework for building production-ready LLM applications in Python.

Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Build scalable RAG systems, multimodal applications, semantic search, question answering, and autonomous agents, all in a transparent architecture that lets you experiment, customize deeply, and deploy with confidence.

Table of Contents

Installation

The simplest way to get Haystack is via pip:

pip install haystack-ai

Install nightly pre-releases to try the newest features:

pip install --pre haystack-ai

Haystack supports multiple installation methods, including Docker images. For a comprehensive guide, please refer to the documentation.

Documentation

If you're new to the project, check out "What is Haystack?" then go through the "Get Started Guide" and build your first LLM application in a matter of minutes. Keep learning with the tutorials. For more advanced use cases, or just to get some inspiration, you can browse our Haystack recipes in the Cookbook.

At any given point, hit the documentation to learn more about Haystack, what it can do for you, and the technology behind.

Features

Agents built for production
Extend agent behavior with lifecycle hooks (before_llm, before_tool, on_exit, …) for guardrails and custom logic, and track step_count, token_usage, and tool calls out of the box for monitoring and cost control. Get started fast with ready-made agents from Agent Pack (e.g., a deep research agent, or an advanced RAG agent) or give your own agents progressive skill discovery via SkillToolset, so skill descriptions only enter context when needed.

Built for context engineering
Design flexible systems with explicit control over how information is retrieved, ranked, filtered, combined, structured, and routed before it reaches the model. Define pipelines and agent workflows where retrieval, memory, tools, and generation are transparent and traceable.

Native Async Support
One Pipeline runs synchronously or asynchronously and streams token by token. Agent can run concurrent tool calls.

Modular and customizable
Use built-in components for retrieval, indexing, tool calling, memory, and evaluation, or create your own. Add loops, branches, and conditional logic to precisely control how context moves through your pipelines and agent workflows.

Model- and vendor-agnostic
Integrate with OpenAI, Mistral, Anthropic, Cohere, Hugging Face, Google, Azure OpenAI, AWS Bedrock, local models, and many others. Swap models or infrastructure components without rewriting your system.

Extensible ecosystem
Build and share custom components through a consistent interface that makes it easy for the community and third parties to extend Haystack and contribute to an open ecosystem.

[!TIP]

Would you like to deploy and serve Haystack pipelines as REST APIs or MCP servers? Hayhooks provides a simple way for you to wrap pipelines and agents with custom logic and expose them through HTTP endpoints or MCP. It also supports OpenAI-compatible chat completion endpoints and works with chat UIs like open-webui.

Haystack Enterprise: Support & Platform

Get expert support from the Haystack team, build faster with enterprise-grade templates, and scale securely with deployment guides for cloud and on-prem environments with Haystack Enterprise Starter. Read more about it in the announcement post.

👉 Get Haystack Enterprise Starter

Need a managed production setup for Haystack? The Haystack Enterprise Platform helps you build, test, deploy and operate Haystack pipelines with built-in observability, collaboration, governance, and access controls. It’s available as a managed cloud service or as a self-hosted solution.

👉 Learn more about Haystack Enterprise Platform or try it free

Telemetry

Haystack collects anonymous usage statistics of pipeline components. We receive an event every time these components are initialized. This way, we know which components are most relevant to our community.

Read more about telemetry in Haystack or how you can opt out in Haystack docs.

🖖 Community

If you have a feature request or a bug report, feel free to open an issue in GitHub. We regularly check these, so you can expect a quick response. If you'd like to discuss a topic or get more general advice on how to make Haystack work for your project, you can start a thread in Github Discussions or our Discord channel. We also check 𝕏 (Twitter) and Stack Overflow.

Contributing to Haystack

We are very open to the community's contributions - be it a quick fix of a typo, or a completely new feature! You don't need to be a Haystack expert to provide meaningful improvements. To learn how to get started, check out our Contributor Guidelines first.

There are several ways you can contribute to Haystack:

[!TIP] 👉 Check out the full list of issues that are open to contributions

Organizations using Haystack

Haystack is used by thousands of teams building production AI systems across industries, including:

Are you also using Haystack? Open a PR or tell us your story

Frequently asked questions

Is haystack free to use?

haystack is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does haystack do?

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

What is haystack written in?

haystack is primarily written in Python. Its source is publicly available at https://github.com/deepset-ai/haystack, and it has 26,913 GitHub stars.