Match the project to your task before installing it.
Research & Knowledge Management · Public
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.
Best fitUsers who want source-backed project understanding before installing it.
Check whether this project matches your task before installing it.
What it can doskill, recipe, host_instruction, eval, preflightReview the portable capability path.
Before continuingVerify in a sandboxDo not treat a preview pack as a proven local install.
GitHub snapshot25k stars2.8k forks · 354 contributors
Publication status · 2026-05-25
What is 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.
- Best fit: Users who want source-backed project understanding before installing it.
- Not for: Not for users who want to skip sandbox verification or cannot accept configuration, permission, or maintenance overhead.
- Capability added to an AI workflow: skill, recipe, host_instruction, eval, preflight
- First safe verification step: Verify the smallest path in an isolated environment and keep a rollback path.
- Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
- Top risk: Do not treat publication status as proof that install, runtime, or host loading has passed.
- Evidence base: https://github.com/deepset-ai/haystack, https://github.com/deepset-ai/haystack#readme, Human Manual, Pitfall Log
01
Quick decision
Use this section to decide whether the project is worth a deeper read.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.
25k stars · 2.8k forks
02
What it can do
Translate the upstream project into concrete capabilities the user can judge before installing.Introduction to Haystack
Related topics: Pipeline Architecture, Core Concepts
Sources: [README.md:1]()()
Pipeline Architecture
Related topics: Introduction to Haystack, Pipeline Component Types, Core Concepts
Sources: [docs-website/docs/concepts/pipelines.mdx](https://github.com/deepset-ai/haystack/blob/main/docs-website/docs/concepts/pipelines.mdx)
Core Concepts
Related topics: Pipeline Architecture, Pipeline Component Types, Introduction to Haystack
Sources: [README.md](https://github.com/deepset-ai/haystack/blob/main/README.md)
Pipeline Component Types
Related topics: Pipeline Architecture, Data Processing Components, LLM and Embedder Integrations
Sources: [docs-website/docs/pipeline-components/converters.mdx]()
Data Processing Components
Related topics: Document Stores and Retrievers, Pipeline Component Types
Sources: [docs-website/docs/pipeline-components/preprocessors/documentsplitter.mdx](https://github.com/deepset-ai/haystack/blob/main/docs-website/docs/pipeline-components/preprocessors/documentsplitter.mdx)
Sources: https://github.com/deepset-ai/haystack, Human Manual, Project Pack evidence, and downstream validation signals.
03
Community Discussion Evidence
Project-level external discussion stays visible on the detail page, not only inside the manual.Community Discussion Evidence
12 source-linked itemsReview these external discussions before using haystack with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.
-
01
EnvVarSecrets: add multi-tenant context support (ContextVar / pipeline-r
github / github_issue
-
02
feat: add INTERSECTION join mode to DocumentJoiner
github / github_issue
-
03
DocumentJoiner concatenate mode incorrectly drops documents with score=0
github / github_issue
-
04
feat: Add `run_async` to `MultiQueryEmbeddingRetriever`, `MultiQueryText
github / github_issue
-
05
MCP Server for Haystack docs
github / github_issue
-
06
RFC: Signed receipts for Haystack pipeline component calls
github / github_issue
-
07
[FEATURE] Support for code syntax-aware Document Splitters
github / github_issue
-
08
Security: OWASP Agent Memory Guard for pipeline memory poisoning defense
github / github_issue
-
09
feat: support token-based budget in LostInTheMiddleRanker
github / github_issue
-
10
docs: Update Ragas docs
GitHub / issue
- 11
-
12
v2.25.2
GitHub / issue
04
How to start
Only source-backed commands are shown here. Verify them in an isolated environment first.Try the prompt first
Test the workflow without installing the upstream project.
previewRead the Human Manual
Understand inputs, outputs, limits, and failure modes.
manualTake context to your AI host
Use the compiled assets in your preferred AI environment.
contextRun sandbox verification
Confirm install commands and rollback before using a primary environment.
verifypip install haystack-aiOfficial start command · https://github.com/deepset-ai/haystack#readme · verified: yes
05
Human Manual
The English page must expose the real manual, not a short placeholder.8+ sections · Human Manual
haystack Manual
Haystack follows a component-based architecture where pipelines serve as the foundational building blocks. Pipelines connect various components including document stores, retrievers, reade...
Open the full manual- haystack Human Manual
- Table of Contents
- Introduction to Haystack
- Related Pages
- What is Haystack?
- Core Capabilities
- Architecture Overview
- Pipeline Components
Introduction to Haystack
Related topics: Pipeline Architecture, Core Concepts
Sources: [README.md:1]()()
Pipeline Architecture
Related topics: Introduction to Haystack, Pipeline Component Types, Core Concepts
Sources: [docs-website/docs/concepts/pipelines.mdx](https://github.com/deepset-ai/haystack/blob/main/docs-website/docs/concepts/pipelines.mdx)
Core Concepts
Related topics: Pipeline Architecture, Pipeline Component Types, Introduction to Haystack
Sources: [README.md](https://github.com/deepset-ai/haystack/blob/main/README.md)
Pipeline Component Types
Related topics: Pipeline Architecture, Data Processing Components, LLM and Embedder Integrations
Sources: [docs-website/docs/pipeline-components/converters.mdx]()
Data Processing Components
Related topics: Document Stores and Retrievers, Pipeline Component Types
Sources: [docs-website/docs/pipeline-components/preprocessors/documentsplitter.mdx](https://github.com/deepset-ai/haystack/blob/main/docs-website/docs/pipeline-components/preprocessors/documentsplitter.mdx)
06
AI Context Pack and portable assets
After deciding to continue, take the project context into your own AI host.Complete pack plus user-owned assets
These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.
07
Preflight checks
Treat this page as a planning asset, not proof that your local environment is ready.- The manual is generated from source-linked project files and Doramagic validation signals.
- Community evidence warnings stay visible instead of being converted into marketing claims.
- This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
- Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.
08
Pitfall Log and verification risks
Doramagic surfaces high-risk items before users treat a candidate capability as verified.Review upstream issue
The source signal needs review before production use.
Review upstream issue
The source signal needs review before production use.
Review upstream issue
The source signal needs review before production use.
Review upstream issue
The source signal needs review before production use.
Review upstream issue
The source signal needs review before production use.
Review upstream issue
The source signal needs review before production use.
Review upstream issue
The source signal needs review before production use.
Review upstream issue
Developers may fail before the first successful local run: Proposal: Transaction Protocol for idempotent, auditable agent pipelines