We are thrilled to be among the ten finalists for The Spark – The Technology Award. For eleven years, @handelsblatt and @McKinsey have been recognizing Germany’s most innovative technology startups. This year’s theme is "Scaling Deep Tech", focusing on technologies that are already making a real-world impact today and shaping the future of industry and the economy. Now, we need your support. Vote by September 7th to help us reach the Top 3! Your vote counts directly toward the jury's decision. Vote for us here: lnkd.in/e49kgusV

📣 We're hosting our next unconference in Berlin with @prior_labs, exploring open-weight models and open-source agents! Come join us if you'd like to discuss: → Structured data in agentic workflows → When agents should hand off to TabPFN for prediction → Benchmarking tabular models vs. LLMs → Why orchestration matters for production agents → What owning your stack end-to-end actually requires → Open-weight vs. closed models in practice Or anything else that's been challenging you lately! 📍 @deepset_ai HQ, Berlin 🗓️ September 24th, 6PM-9PM Register: luma.com/haystack-priorlabs

We’re proud to be named one of the @Siftedeu 100 Fastest Growing Startups in DACH & CEE. For us, this recognition marks another step in our mission to help organisations build and scale sovereign AI on their own terms. With Haystack, we’re helping enterprises and public sector teams turn AI systems and agents into production applications that are controllable, adaptable, and built to deliver real business outcomes. Check out more in the full report: sifted.eu/intelligence/repor… #Sifted100 #SiftedLeaderboards

🗽In NYC tonight? @DylanCouzon & @qdrant_engine are hosting a debate night, and @deepset_ai is teaming up Hear some hot AI takes, get a chance to win prizes, and learn about @Haystack_AI and @qdrant_engine along the way! luma.com/nyc-meetup-qdrant-0…

Work on a production-grade AI agent is never really finished. You ship it, watch how it behaves, and keep improving it. But that cycle only works if you can see what is happening inside every run. Getting that visibility often meant sending prompts, responses, and trace data to a separate third-party tool. Until now - we are launching Traces in Haystack Enterprise Platform: full observability for every pipeline, built directly into the platform that runs it. → See every run end to end: spans, tokens, inputs, outputs, logs, errors → Read the root cause in seconds, and tell a config error from a provider timeout → Compare two pipeline versions to see what a change cost before you ship it → All on your own infrastructure. Your data never leaves. Build, run, and improve your agents with full visibility at every step - all on one platform. Read the blog to see Traces in action: deepset.ai/blog/traces-relea…

The new “The Top 10 Trends In Sovereign AI, 2026” research authored by @forrester Principal Analyst Dario Maisto explores how organizations are redefining Sovereign AI not as isolation, but as architectural choice. We're proud to see deepset and the Haystack Enterprise Platform recognized, including our work powering the @EU_Commission's AI@EC Platform. Our take: Sovereign AI means the freedom to choose your models, infrastructure, and deployment environment, while retaining full control. Learn more: deepset.ai/news/new-independ… #SovereignAI #Haystack #EnterpriseAI

Haystack 3.0 shipped this month. We spent launch week showing you what it can do. Now here's what it took to build it 👇 Since @Haystack_AI 2.0: 2,400+ pull requests merged, 195 contributors, ~170 of them making their first-ever contribution along the way. 17,258 CI runs since the v3 branch was cut, roughly one every five minutes, around the clock, for eight weeks. Most-edited file of the whole cycle: agent.py. Of course it was. Migrating to 3.0? The full guide covers all breaking changes: docs.haystack.deepset.ai/doc… Or skip straight to haystack-v2-to-v3, an agent skill that migrates your v2 pipelines and agents for you. 💙 Huge thanks to our open-source team at @deepset_ai, and to our community contributors who shipped fixes and features for v3 alongside us! Haystack 3.0 is yours as much as it's ours. Got questions about migrating, or curious why we made a specific call? Join us at Haystack 3.0 Office Hours next week, August 4, with @LukawskiKacper and @bilgeycl 👉🏼 Register: luma.com/haystack-3

AI sovereignty has become a mainstream enterprise priority. But the conversation often centers on a single question: Where does the model run? That's only part of the story. When you deploy AI agents in production, the real value accumulates around the model: the skills that encode how your team works, along with the tools, memory, workflows, and context unique to your organization. Models can be replaced. This agent orchestration layer cannot. The more important question becomes: Who controls that layer? If your skills, logic, and context only work inside a single vendor's runtime, lock-in hasn't disappeared. It has simply moved from the model to the orchestration layer around it. Today we're excited to introduce Haystack 3.0, designed to keep that layer open and under your control: → Portable skills you can read, version, and own → A programmable agent loop you can inspect, audit, and adapt → Built-in observability into how your agents think and operate Every AI agent runs inside an orchestration layer. True AI sovereignty means owning the agent orchestration layer, not just choosing where the model runs. With 3.0, that control stays in your hands: open source, model-agnostic, infrastructure-independent, and designed to keep the most valuable part of your AI system yours. @malte_pietsch dives deeper into this idea in his latest post: deepset.ai/blog/haystack-3-s…

What a search week in Berlin! 🇩🇪 On Tuesday, we hosted "Retrieve. Remember. Reason" at the @deepset_ai offices, organized with @OpenSearchProj and @cognee_, featuring Women of Search (@atitaarora 🙏), where I got to demo what's possible with a knowledge base, memory, and @Haystack_AI's orchestration capabilities. More than half the room was women, which is rare and wonderful at tech meetups! 🫶 Then yesterday, I joined the Vector Space Meetup panel at @aicampusberlin, alongside @qdrant_engine, @cognee_, @llama_index, and @n8n_io, to talk about retrieval strategies, evaluation, orchestration, and what actually goes into production. Great panel and amazing networking session! Kudos to @krotenWanderung and the team It was a great week where I learned so much. Already looking forward to the next thing!

Haystack now publishes a public Model Context Protocol server. Point Claude Code, Cursor, or any MCP-compatible coding agent at it and get real-time access to the latest Haystack docs - no API keys or sign-ups needed. 🖇️ docs.haystack.deepset.ai/doc…

We over-trust LLMs, but not worry enough about the agentic loop around them when building agents At my @pyconit talk yesterday, I shared why agents fail and how a solid agent harness can fix them, code & slides below 👇

Can't wait to be back in Bologna for @pyconit this week! I'm talking about why agents fail and how to fix them, with a live demo of our itinerary agent built using context-engineering patterns and @Haystack_AI! See you all there 🙌

WHAT AN EVENT!! 🎉 Last week we hosted an unconference as @deepset_ai with @NVIDIA at @balderton office in London. 🎙️ We kicked off with two short talks. @LukawskiKacper demoed a multi-agentic post-event report creator built with @Haystack_AI and Nemotron 3 Super, @KarinSevegnani walked us through Nemotron 3's performance and benchmarks. 💬 Then we split into three discussion groups and I led a session on memory and long running agents. One of the most interesting conversations I've had in a while. We started with memory and second brain concepts. People shared how they're building personal agents by transcribing YouTube videos and creating knowledge bases following @karpathy's wiki idea. We talked RAG vs filesystems, MCPs vs skills, AI sovereignty and security. At the end of the day, you don't want to lock your whole identity to an API, privacy and freedom of choice matter. Thank you to every attendee for your energy, openness, and contributions. I'm already looking forward to coming back to London 💙 See you at Unconference #4 👀

⭐ @Haystack_AI just crossed 25,000 stars on GitHub! This number means a lot to us, but what it really represents is you. Every contributor who opened a pull request. Every community member who answered a question on Discord. Every developer who filed an issue, wrote a notebook, gave a talk, or simply built something incredible with Haystack and shared it with the world. It's a true community effort 💙 When we first started Haystack, we believed that the journey to building great AI applications should be open, composable, and community-driven. 25,000 stars later, that belief has never felt more validated. Thank you to every single one of you: contributors, users, advocates, and builders. Let’s keep going! 🚀

London people 👋 We're hosting an unconference with @nvidia on April 29th! 💂 This is our third unconference at @deepset_ai and if you haven't been to one before, it's very different from a typical meetup. Instead of talks, there are round table discussions with practitioners working through real context engineering challenges. Expect networking and genuine technical conversations. + we'll be talking about nemotron models and @LukawskiKacper is going to show a live demo. 📅 April 29, 6 PM 📍 @balderton offices Looking forward to the discussions!

⚡ We're proud to partner with @mozilla on #Thunderbolt to deliver a complete sovereign AI stack for enterprises and public sector organizations that need full control over how AI is built, deployed, and used. Together, Thunderbolt and @Haystack_AI give organizations a self-hostable AI client paired with the infrastructure to run agents, RAG pipelines, and AI workflows on your organization's actual data. Deployed within your infrastructure, free from vendor lock-in. Learn more about our partnership here: thunderbolt.io/announcing-th…

Looking forward to @aiDotEngineer next week! 🇪🇺 AI Engineer Paris was one of the best conferences I attended last year, and I'm so excited to be speaking at AI Engineer Europe this year alongside so many brilliant minds. I'll be talking about something that doesn't get enough attention in engineering conversations: sovereignty constraints for technical folks. I'll share real engineering trade-offs and what building under these constraints actually looks like in practice, drawing from my work at @deepset_ai. Hope to see you there, come say hi if you're around! 👋

We hosted the second Unconference in Munich 🇩🇪 with @cognee_, @qdrant_engine , and @deepset_ai, and it was 🔥 The discussions focused on Context Engineering with Open-Source: - How do we get the right context in? - Context in Agentic Systems - Context Engineering in Production …but honestly, we covered everything from automatic ontology generation to coding agents. 💡 One thing I learned: Coding agents often struggle with multiple iterations, partly because MoE models behave differently as context grows. This is why I love hosting and attending these events: you learn from people who are actually building these AI systems and making them work. Huge thanks to everyone who joined 🙌 And kudos to the amazing organizer team: @HandexxK , @krotenWanderung , Paula Plattner 💜 👉 We'll keep on organizing them in different cities. Where should we go next?

🚀 @GoogleDeepMind just launched Gemini Embedding 2 today and Haystack supports it from Day 0. Embed text, images, video, audio, and PDFs into one vector space and build multimodal search or cross-modal retrieval systems. Learn how in our latest blog post 👇 haystack.deepset.ai/blog/mul…

🚀 Haystack 2.25 is here! This release focuses on improving the user experience of the Agent component and making tool selection more scalable and efficient. 🛠️ Dynamic Tool Discovery with SearchableToolset With SearchableToolset, agents dynamically discover relevant tools using BM25 keyword search instead of exposing hundreds of tools to the LLM upfront. This approach: – Reduces LLM context usage (and token costs) – Improves tool selection accuracy – Works especially well when connecting to MCP servers Agents load only the tools they actually need, making large tool ecosystems practical without overwhelming the model. 📝 Reusable Jinja2 Prompt Templates for Agents Agents now natively support templated` user_prompt` and `required_variables`, simplifying how you structure and invoke agents. With this update, you can define prompts once and pass variables at runtime. This means: – Less boilerplate – Cleaner agent invocation – More reusable and maintainable agent workflows 💙 Big thanks to our contributors to this release! 👇 Full release notes in the next post Explore the release and let us know what you build with it 💬