Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Haystack by deepset

deepset's open-source framework for building production LLM pipelines and agents, with a focus on retrieval.

Agent frameworks and SDKs LLM pipeline frameworkOpen source · Apache-2.0Free to start

Use it in: API / SDK Works with: MCP Local models Multi-agent

Price
Free (OSS)
free and open source
Popularity
#19 in Frameworks
Gid Score 49 / 100 · #19 of 50 ranked frameworks and SDKs
Trend
Growing
downloads up 18.8% over 30 days · up 19.7% last week
Development
Actively updated
latest 3.5.0, 10d ago
Community
27.1K GitHub stars
177K package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What Haystack does

Haystack is a LLM pipeline framework from deepset, first released in November 2019. You use it through a Python library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Anthropic, Google, Mistral, Amazon Bedrock and Azure. It is used from Python. It is free and open source (Apache-2.0); you pay only for the models it calls.

Key facts

Makerdeepset
TypeLLM pipeline framework
First releasedNovember 2019
LicenseApache-2.0
InterfacesPython library
Main languagePython
Open issues and PRs169

Pricing

Haystack is open source and free to use; you pay only for the models and infrastructure it runs on.

Checked Nov 4, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (Apache-2.0)
  • Where you use itPython library
  • Supports MCP?Yes
  • Model providersopenai, anthropic, google, mistral, amazon, azure, local
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeLangChain · all alternatives

What's new in Haystack: November 2026 so far

Full monthly summary

November brought dependency updates for security and API compatibility, along with several important changes to how Haystack handles data and integrates with OpenAI's latest models. Users upgrading to version 3.5.0 should review breaking changes around Excel parsing, state keys, and OpenAI model defaults.

Action needed: Minimum OpenAI SDK version raised from 2.6.0 to 3.26.0.
  • OpenAI SDK minimum version raised to 3.26.0 to support the Decisions API.
  • Default OpenAI model changed from gpt-5-mini to gpt-5.6-terra.
  • Excel parser now preserves text like "NA" and "NULL" instead of treating them as missing values by default.
  • Variadic and multi-sender list inputs now respect connection order in pipelines.

2 releases this month · summarised from the official release notes · all months

AgentGid articles about Haystack

All guides

Get started with Haystack

PyPIpip install haystack-ai

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Add-ons for Haystack: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for Haystack or for agent frameworks in general. Savings and results depend on your workload.

Compare Haystack with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
1
LangChainLangChain
79 41.1M up 5.7% down 2.7% 150K+76/day 1.5.22d ago Free (OSS)
2
LangGraphLangChain
75 20.1M up 5.5% up 29.2% 45.1K+48/day 1.2.23yesterday Free (OSS)
3
AI SDKVercel
68 47.2M up 3.9% up 38.4% 28.1K+30/day 7.0.1772d ago Free (OSS)
4 64 29.3M up 5.9% up 37.6% 8,588+9/day 0.2.185yesterday Free (OSS)
5
MastraMastra
63 3.7M up 14.9% up 49.9% 29.6K+23/day 1.84.02d ago Free (OSS)
6 62 7.2M up 4.8% up 38.9% 30.8K+21/day 0.25.02d ago Free (OSS)

Tools used with Haystack

All tools

What 124 public GitHub projects that depend on Haystack use with it, from their dependency files.

  1. python-dotenv53.2%
  2. Sentence Transformers47.6%
  3. pandas46.0%
  4. Requests37.9%
  5. OpenAI Python Library37.9%
  6. tqdm36.3%
  7. Hugging Face Transformers35.5%
  8. NumPy34.7%
  9. PyPDF31.5%
  10. Pydantic31.5%

Used far more often here than in AI-built projects overall: what sets Haystack projects apart.

  1. PostHog21.8% · 151.3×
  2. backoff21.8% · 136.2×
  3. more-itertools21.8% · 113.5×
  4. Hugging Face Datasets25.0% · 60.1×
  5. tokenizers16.9% · 42.4×
  6. distro22.6% · 40.3×
  7. fsspec16.9% · 37.8×
  8. attrs21.0% · 31.2×

Ratings from people who use Haystack

No ratings yet. Used Haystack? Rate it and say what it is good and bad at.

Haystack news

All AI agent news

  1. Release GitHub Releases

    Haystack 3.5.0 released

    Raise the minimum supported openai SDK version from 2.6.0 to 3.26.0 to support the Decisions API.; Declared pydantic>=2.12 (>=2.14 on Python 3.15) as the minimum supported version.; If you don't set keep_default_na or na_values in read_excel_kwargs…

What changed: recent Haystack releases

8 stable releases in the last 90 days · Monthly summary · Full changelog

3.5.0
  • Raise the minimum supported openai SDK version from 2.6.0 to 3.26.0 to support the Decisions API.
  • Declared pydantic>=2.12 (>=2.14 on Python 3.15) as the minimum supported version.
  • If you don't set keep_default_na or na_values in read_excel_kwargs, XLSXToDocument now keeps cell text such as "NA", "N/A", "NULL", and "None" instead of treating it as missing.
  • Components with a Variadic input, or a list input connected to several senders, now receive the values in the order the senders were connected with Pipeline.connect().
  • The default model of OpenAIChatGenerator and OpenAIResponsesChatGenerator changed from gpt-5-mini to gpt-5.6-terra, the replacement OpenAI recommends.
  • If you read id, encrypted_content, or status directly from reply.reasoning.extra in OpenAIResponsesChatGenerator replies, read them from entries in reply.reasoning.extra["reasoning_items"] instead.
2.31.1
  • Haystack now requires anyio>=4.14.2. anyio is installed transitively through httpx and openai; versions before 4.14.2 are affected by CVE-2026-63374 (GHSA-82r6-8w77-94w6).
  • Haystack now requires certifi>=2026.10.19. certifi is installed transitively through httpx and posthog.
Earlier releases
3.4.1
  • Haystack now requires certifi>=2026.10.19. certifi is installed transitively through httpx and posthog.
3.4.0
  • The page_number metadata field now means the same thing in every splitter: the page the chunk's text starts on. Two cases change
  • RecursiveDocumentSplitter reported the page a chunk ended on. A chunk spanning a page break now reports the page it starts on, matching DocumentSplitter and MarkdownHeaderSplitter.
  • DocumentSplitter, MarkdownHeaderSplitter and EmbeddingBasedDocumentSplitter reported the previous page for a chunk that began with one or more form feeds (\f), even though all of the chunk's text…
  • RecursiveDocumentSplitter with split_unit="word" and split_overlap greater than 0 now returns chunks copied from the document as they are.
  • RecursiveDocumentSplitter now keeps the whitespace between sentences when sentence_splitter_params sets keep_white_spaces to False.
  • Dropped support for Python 3.10 since it reaches End of Life (EOL) in October 2026. The minimum supported Python version is now 3.11.
3.3.0
  • InMemoryDocumentStore.bm25_retrieval and InMemoryBM25Retriever with BM25L (the default) or BM25Plus now return only documents that contain at least one query term, with or without scale_score.
  • TextCleaner.run now raises a clear TypeError when texts is not a list or any element is not a str, instead of failing later or producing unexpected results.
  • Haystack now requires anyio>=4.14.2. anyio is installed transitively through httpx and openai; versions before 4.14.2 are affected by CVE-2026-63374 (GHSA-82r6-8w77-94w6).
  • Fixed BM25 tokenization in InMemoryDocumentStore for Chinese, Japanese and Korean text.
  • Fix Pipeline.connect() raising TypeError: object of type 'ellipsis' has no len() when one of the sockets is annotated with Callable[..., T].
  • Fixed ChatPromptBuilder dropping content parts when the template is a list of ChatMessage objects.
3.2.0
  • Serialized OutputAdapter and ConditionalRouter components containing Jinja custom_filters must now be loaded with Pipeline.load(..., unsafe=True)…
  • The tool_result_offloaded meta key that the hook sets on an offloaded message now always holds a list of store references rather than a single reference string, since a result can span several…
  • The + operator for combining Toolsets has been removed. Pass Toolsets as a list wherever tools are accepted instead: Agent(..., tools=[toolset_a, toolset_b]).
  • Toolset.add() now only accepts a single Tool, not another Toolset. To combine Toolsets, pass them as a list: Agent(..., tools=[toolset_a, toolset_b]).
  • Add Pipeline.add_components() to add a mapping of component names to component instances in one call.
  • Added the experimental SummarizationCompactor (use with CompactionHook), which progressively summarizes a conversation until it fits a target token budget, preserving useful context from…

Haystack prices over time

Token prices of OpenAI modelsnewest OpenAI model in each family, output price per 1M tokens
OpenAI FlagshipOpenAI Mini

Haystack popularity and usage data

Haystack was downloaded 177K times from PyPI in the week ending Nov 17, 2026, up 19.7% on the week before and up 18.8% over the last 30 days compared with the 30 before. The GitHub repository has 27.1K stars, 302 of them added in the last 30 days. The latest stable release is 3.5.0, published Nov 10, 2026; there were 3 stable releases in the past 30 days.

Downloads per dayPyPI, 7-day average 25.3K/day
GitHub starsrunning total 27.1K

Download the raw daily series: haystack.csv

Gid Score breakdown

Adoption50
Community60
Attention—
Momentum59

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Haystack FAQ

How much does Haystack cost?

Haystack is open source and free to use; you pay only for the models and infrastructure it runs on.

Is Haystack open source?

Yes. Haystack is open source, released under the Apache-2.0 license.

How popular is Haystack?

Haystack was downloaded 177K times from PyPI in the week ending Nov 17, 2026, up 19.7% on the week before and up 18.8% over the last 30 days compared with the 30 before. The GitHub repository has 27.1K stars, 302 of them added in the last 30 days. The latest stable release is 3.5.0, published Nov 10, 2026; there were 3 stable releases in the past 30 days.

What is the latest version of Haystack?

The latest stable release we track is 3.5.0, published on Nov 10, 2026.

What are the alternatives to Haystack?

The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.

For the makers of Haystack badges, corrections

Add a live badge to your README or site:

AgentGid: #19 in Frameworks Gid Score: 49/100 downloads: 177K/week ▲19% 30d

[![AgentGid: #19 in Frameworks](https://agentgid.com/badges/haystack-rank.svg)](https://agentgid.com/agents/haystack/)
[![Gid Score: 49/100](https://agentgid.com/badges/haystack-score.svg)](https://agentgid.com/agents/haystack/)
[![downloads: 177K/week ▲19% 30d](https://agentgid.com/badges/haystack-downloads.svg)](https://agentgid.com/agents/haystack/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: haystack-ai. GitHub: deepset-ai/haystack. See data sources for how each one is collected.