Haystack: Build Scalable LLM Apps with 27k+ GitHub Stars
From the repo · “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.”
Build modular AI pipelines with Haystack to create scalable large language model applications.
"A founder of a startup wants to build a conversational chatbot that can answer customer questions about their products. They use Haystack to design a modular pipeline that integrates with their product database and a large language model. After setting up the pipeline, the founder can test the chatbot and refine its performance to provide accurate and helpful responses to customers."
- •Creating enterprise search systems with semantic document retrieval
- •Building conversational AI agents with context-aware memory and routing
- •Developing RAG (Retrieval-Augmented Generation) applications with custom knowledge bases
from haystack import Pipeline pipeline = Pipeline() pipeline.add_node(retriever, name='retriever', inputs=['Query']) pipeline.add_node(reader, name='reader', inputs=['retriever']) result = pipeline.run(query='What are the key benefits of AI for startups?')
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
A prompt/skill package — nothing to install beyond adding it to your AI tool.
mkdir -p ~/.claude/skills/haystack && curl -fsSL https://workflowstacks.com/api/skills/haystack/claude-skill -o ~/.claude/skills/haystack/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Haystack: Build Scalable LLM Apps with 27k+ GitHub Stars is mostly documents (8613 doc files, 301 small scripts) — something you read, not something you run. There is nothing to install. Last commit this month, Apache-2.0 license.
- 1README.mdStart here — what it does and how to install it
- 2AGENTS.mdThe instructions the AI actually follows
- 3haystack/__init__.pyInside haystack/ — the main logic begins here
- 4examples/README.mdA worked example — copy this to get going
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
A prompt/skill package — nothing to install beyond adding it to your AI tool.
mkdir -p ~/.claude/skills/haystack && curl -fsSL https://workflowstacks.com/api/skills/haystack/claude-skill -o ~/.claude/skills/haystack/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/haystack?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Do this with a working workflow
Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.
AI Support Agent (Chat)
A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.
MCP configGitHub MCP config
Search repos, read code, open issues and PRs from Claude.
MCP configPuppeteer (browser) MCP config
Let Claude control a headless browser — navigate, screenshot, scrape.
Related skills
More mcp-server tools founders pair with this one.