Skip to main content

deepset

deepset makes Haystack, an open-source Python framework for building AI agents and retrieval-augmented generation (RAG) applications, and sells an enterprise platform on top of it. The platform lets teams build, test, deploy and govern AI applications in the cloud or on their own infrastructure. Customers include the European Commission, Bosch and the German Federal Ministry of Research, Technology and Space.

Traction 10/10
Berlin, Germany · HQ
Founded 20188420K+ followers
  • AI Agents
  • Artificial Intelligence
  • Enterprise Software
  • Software Only
Updated today

Funding

Raised to date

$45.8MRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.

Funding rounds are not available yet.

Founders

2 founders

Milad Mahmoodian

Co-Founder/CEO

Timo Molt

Co-Founder/CTO

Product

Problem

Companies want AI assistants and agents that answer from their own documents and systems, but most AI platforms decide where the software runs, which models it uses and where data can go. Regulated organizations need to keep those choices themselves.

Solution

deepset maintains Haystack, an open-source framework in Python for building AI agents and RAG pipelines, the setups that let a model look up documents before answering. Teams compose a pipeline from components such as retrievers, tools and memory, and can swap models, data stores or infrastructure without rebuilding. The Haystack Enterprise Platform adds a visual builder, a debugger and templates, plus side-by-side testing of prompts and retrieval strategies. It deploys to a managed cloud or self-hosted, with serverless execution that scales automatically. Run history, traces, role-based access control and audit logs let teams monitor and govern what the agents do.

Target Audience

AI product teams, data scientists and software developers at enterprises and public-sector bodies that need to run AI on their own infrastructure.

Features

  • Build agents and RAG pipelines in a visual builder, then export them as Python or YAML.
  • Compare prompts, retrieval strategies and agent workflows side by side before release.
  • Deploy with one click to a managed cloud or self-hosted environment, with a REST API.
  • Swap models and providers without rewriting application code.
  • Track every query, answer and context source in a unified run history.
  • Enforce guardrails at runtime and keep audit logs for compliance.
This profile is AI-generated and may contain inaccuracies.