- 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.
Haystack by deepset
deepset's open-source framework for building production LLM pipelines and agents, with a focus on retrieval.
Use it in: API / SDK Works with: MCP Local models Multi-agent
On this page
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
| Maker | deepset |
|---|---|
| Type | LLM pipeline framework |
| First released | November 2019 |
| License | Apache-2.0 |
| Interfaces | Python library |
| Main language | Python |
| Open issues and PRs | 169 |
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.
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
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.
- 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
Get started with Haystack
| PyPI | pip 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
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Haystack or for agent frameworks in general. Savings and results depend on your workload.
Haystack alternatives
Best Haystack alternatives compared · All agent frameworks and SDKs
| # | 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 |
Claude Agent SDKAnthropic |
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 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Tools used with Haystack
What 124 public GitHub projects that depend on Haystack use with it, from their dependency files.
- python-dotenv53.2%
- Sentence Transformers47.6%
- pandas46.0%
- Requests37.9%
- OpenAI Python Library37.9%
- tqdm36.3%
- Hugging Face Transformers35.5%
- NumPy34.7%
- PyPDF31.5%
- Pydantic31.5%
Used far more often here than in AI-built projects overall: what sets Haystack projects apart.
- PostHog21.8% · 151.3×
- backoff21.8% · 136.2×
- more-itertools21.8% · 113.5×
- Hugging Face Datasets25.0% · 60.1×
- tokenizers16.9% · 42.4×
- distro22.6% · 40.3×
- fsspec16.9% · 37.8×
- 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
-
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
- 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
- Haystack now requires certifi>=2026.10.19. certifi is installed transitively through httpx and posthog.
- 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.
- 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.
- 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
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.
Download the raw daily series: haystack.csv
Gid Score breakdown
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
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 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:
[](https://agentgid.com/agents/haystack/)
[](https://agentgid.com/agents/haystack/)
[](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.