About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Article
Open source LLMs unlock agentic and generative AI
Dive into gen AI and automation technologies with these hands-on workshops
On this page
Open source LLMs provide transparency and flexibility regardless of whether they're accessed on the cloud or on premises. They give you full control over your data and the ability to keep your own sensitive information within your network, ensuring your security stays strong.
An open source LLM offers transparency in its function, architecture, and training data. You have visibility into algorithms and can ensure ethical and legal compliance, and if you choose to optimize an open source LLM, you can improve its performance.
Bottom line? Open source LLMs come with huge benefits that you can't afford to ignore. But how do you get started?
Open source LLMs playlist now available
The recent IBM TechXchange Dev Day: Open Source LLMs digital learning event was designed for AI developers, data scientists, integration developers, administrators, and engineers. The session recordings from that event are now available in a new Open Source LLMs playlist on the IBM Developer YouTube channel.
This set of workshops will jump-start your LLM and generative AI skills and help you dive into AI agents and assistants. With over 12 hours of AI and open source content, this is your opportunity to learn from IBM experts and quickly advance your AI journey from experimentation to deployment.
Two themes
The workshops were divided into two distinct tracks, "Getting started with gen AI" and "Applied AI."
Getting started with gen AI: AI agents are pushing the boundaries of machine intelligence, combining large language models with dynamic reasoning, planning, and tool use. By orchestrating these components, they can autonomously tackle a wide range of complex, multi-step tasks. Dive into the world of AI agents:
- Build your own custom agent
- Learn how to troubleshoot performance
- Expose your agent via an API
Applied AI: Follow along as IBM experts dive into the newly released IBM Granite foundation models, which are designed for the enterprise and optimized for business domains and use cases.
Coding sessions with IBM expert
The IBM TechXchange Dev Day: Open Source LLMs sessions are designed for practitioners like you. You'll find code-level content and real-world examples and demos that will help take your gen AI projects from idea to implementation.
Featured sessions include:
Video will open in new tab or window
IBM TechXchange Dev Day: Open Source LLMs keynote session
IBM TechXchange Dev Day: Open Source LLMs gives you the chance to learn how to build AI agents and AI assistants during hands-on workshops that delve into generative AI and automation technologies using IBM Granite open source AI models. Whether you're exploring AI-powered coding assistants, developing robust data pipelines and integrations, or pushing the boundaries of generative AI on IBM Z, our sessions provide the insights you need for enterprise AI. Join Nicholas Renotte, Head of AI Developer Advocacy at IBM, as he kicks off the Open Source LLMs Dev Day, featuring over 12 hours of AI and open source content to quickly advance your AI journey from experimentation to deployment.
IBM TechXchange Dev Day: Open Source LLMs gives you the chance to learn how to build AI agents and AI assistants during hands-on workshops that delve into generative AI and automation technologies using IBM Granite open source AI models. Whether you're exploring AI-powered coding assistants, developing robust data pipelines and integrations, or pushing the boundaries of generative AI on IBM Z, our sessions provide the insights you need for enterprise AI. Join Nicholas Renotte, Head of AI Developer Advocacy at IBM, as he kicks off the Open Source LLMs Dev Day, featuring over 12 hours of AI and open source content to quickly advance your AI journey from experimentation to deployment.
Agentic RAG: Build a multi-agent QA chatbot for your documents with RAG, LangGraph and Docling
In this immersive workshop, IBM Data Scientist Hailey Quach shows you how to build DocChat, a multi-agent RAG platform that retrieves, synthesizes, and verifies information from your documents with precision. Unlike traditional chatbots, DocChat combines advanced hybrid retrieval (BM25 + vector search) and multi-agent workflows to cross-check answers. No more hallucinated responses—DocChat delivers fact-based solutions or flags gaps when data is missing. Using LangGraph, Docling, ChromaDB, and Gradio, you’ll learn to deploy reliable AI that excels at real-world document intelligence. Walk away with practical skills to build AI assistants that are transparent, accurate, and production-ready. (Check out Hailey's free guided project!)
Video will open in new tab or window
Build AI Agents with Open Source LLMs on watsonx.ai
AI agents are autonomous systems powered by large language models (LLMs) that can perceive, reason, and act to complete tasks on behalf of users. AI agents can handle complex workflows, dynamically interact with multiple tools, and make decisions based on real-time data. In this session, watsonx.ai Product Manager Vijesh Bhaktha Rajagopal explores how to approach building agents and identify suitable use cases across business functions like customer support, IT automation, and insurance claims. We’ll also walk through how IBM watsonx.ai provides a robust platform to build, test, and deploy AI agents using open source LLMs. Whether you're just getting started or looking to operationalize gen AI in production, this session will give you the foundation and practical approach to unlock value with AI agents on watsonx.ai.
AI agents are autonomous systems powered by large language models (LLMs) that can perceive, reason, and act to complete tasks on behalf of users. AI agents can handle complex workflows, dynamically interact with multiple tools, and make decisions based on real-time data. In this session, watsonx.ai Product Manager Vijesh Bhaktha Rajagopal explores how to approach building agents and identify suitable use cases across business functions like customer support, IT automation, and insurance claims. We’ll also walk through how IBM watsonx.ai provides a robust platform to build, test, and deploy AI agents using open source LLMs. Whether you're just getting started or looking to operationalize gen AI in production, this session will give you the foundation and practical approach to unlock value with AI agents on watsonx.ai.
Video will open in new tab or window
Building AI Applications from Your Desktop with Podman AI Lab
Generative AI is revolutionizing how we build modern applications. But for developers it can be daunting, particularly with evaluating models, building with gen AI, and the path to production. But, it doesn’t have to be worrisome! Using container technology and open source models from Hugging Face, Red Hat Senior Developer Advocate Cedric Clyburn shows how to practically integrate gen AI in an existing application from your local development environment and ultimately deploy it onto Kubernetes. Why work with local and open-source models? From reducing cloud computing costs, keeping control of your sensitive data, and alleviating vendor-locking, it’s an increasingly popular way for developers to prototype AI applications quickly. With the Podman AI Lab, you can run and build applications with generative AI, powered by open source!
Generative AI is revolutionizing how we build modern applications. But for developers it can be daunting, particularly with evaluating models, building with gen AI, and the path to production. But, it doesn’t have to be worrisome! Using container technology and open source models from Hugging Face, Red Hat Senior Developer Advocate Cedric Clyburn shows how to practically integrate gen AI in an existing application from your local development environment and ultimately deploy it onto Kubernetes. Why work with local and open-source models? From reducing cloud computing costs, keeping control of your sensitive data, and alleviating vendor-locking, it’s an increasingly popular way for developers to prototype AI applications quickly. With the Podman AI Lab, you can run and build applications with generative AI, powered by open source!
Additional sessions include:
- Cooking with Granite: Hands-on with IBM's Open Source LLMs
- Boost Developer Productivity with IBM watsonx Code Assistant
- AI Governance at Scale: Leveraging Amazon SageMaker and IBM watsonx.governance
- Turn Environmental Data to Actionable Insights: Explore IBM Environmental Intelligence
- Transforming Industries Through Agentic AI
- Automating IT infrastructures with watsonx Code Assistant for Red Hat Ansible Lightspeed
- Build an AI stylist with IBM Granite using watsonx.ai
Upcoming Dev Days
IBM TechXchange Dev Days are a series of digital and in-person events that give you exclusive access to the latest IBM technology and the experts who know how to get the most out of it.
Next session: AI and Automation Unpacked
Get started today
The AI revolution is accelerating. If you're concerned that you're falling behind, these sessions are perfect for you. Roll up your sleeves, engage with our IBM instructors, and get hands-on with labs that showcase generative and agentic AI.
Check out the Open Source LLMs playlist on the IBM Developer YouTube channel today!
Additional IBM Developer AI resources: