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.
deepset-ai/haystack is an open-source Python framework for assembling AI applications from modular pipelines that handle tasks such as retrieving information, routing requests, managing memory, and generating responses. It is for developers building retrieval-augmented generation, semantic search, question-answering, multimodal, and agent systems. The catalogue instructions relate to working with this framework.
Latest release v3.4.1 · 21 Oct 2026
2 files for Codex, OpenCode and Claude Code: haystack AGENTS.md, haystack CLAUDE.md — 1,902 tokens loaded in every session.
AGENTS.md A 1,897 tok CLAUDE.md A 5 tok These files are deepset-ai/haystack's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.