Harness Hub
All startups

deepset

Enterprise AI platforms around the Haystack framework.

deepset (Berlin) builds the Haystack framework and an enterprise platform for industrial-grade RAG and agent pipelines — a European anchor of the NLP/agent engineering space since 2018.

Pros & cons

Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.

Pros

  • MetadataHaystack is Apache-2.0 (about 27k stars) and gives explicit control over retrieval, ranking and routing, plus agent hooks.[1]
  • DocsIntegrates with OpenAI, Anthropic, Mistral, Cohere, Hugging Face, Google, Azure OpenAI and Bedrock.[1]
  • DocsThe Enterprise Platform is available managed or self-hosted, including on-prem, with governance and access controls.[1]

Cons

  • MetadataEnterprise Platform pricing is quote-based and not public.[1][2]
  • MetadataThe free Studio tier is reportedly capped at about 50 executions per month.[1]
  • DocsObservability, collaboration, governance and access controls are in the paid Enterprise Platform, not the open-source framework.[1]
Best for
Teams building production RAG and search-heavy agents that may need on-prem deployment.
Watch out for
Get a quote early if you plan to use the managed platform.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

Their open-source work

deepset-ai/haystack

Production-grade pipelines and agents for the enterprise.

Maintained by deepset

v3.5.0released

Activity

Last push
· yesterday
Latest release
v3.5.0
· 11d ago
Last 90 days
16 releases
  1. v3.5.0

    · 11d ago

    ⭐️ Highlights 🧭 Classify and Route with the OpenAI Decisions API Three new components use the OpenAI Decisions API to choose how to handle your data without instructions. OpenAIDecisionsTextRouter sends text to a named output per label, OpenAIDecisionsImageRouter does the same…

  2. v3.5.0-rc1Pre-release

    · 12d ago
  3. v2.31.1

    · 2w ago

    🔒 Security Notes 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…

  4. v2.31.1-rc1Pre-release

    · 2w ago
  5. v3.4.1

    · 4w ago

    🔒 Security Notes Haystack now requires certifi=2026.10.19. certifi is installed transitively through httpx and posthog; earlier versions trust eMudhra/emSign certificate authorities whose private keys were compromised (GHSA-6q48-6c7w-9gw2). If you pin certifi, raise the pin to…

Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.

On X

No posts from them in our X feed yet.

Follow @deepset_ai on X · The X feed

Featured

The de-facto standard toolkit for building LLM applications and agents.

LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.

~$75M raised

4 pros · 4 cons
Featured

Conversational AI agents for customer experience.

Sierra, co-founded by Bret Taylor and Clay Bavor, builds production conversational agents that resolve real customer issues with guardrails, evaluation and human escalation — a template for deploying vertical agents at the enterprise edge.

~$10B valuation (Oct 2025)

4 pros · 4 cons

Multi-agent orchestration, from open-source framework to enterprise platform.

CrewAI popularized role-based multi-agent teams ('crews') with a simple mental model and ships an enterprise control plane for deploying, monitoring and governing them.

$18M Series A led by Craft Ventures (2024)

3 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Maintains · 1

Similar entries · 1

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.