Open Source Summit India 2026: Full Schedule

16-17 June, 2026
Mumbai, India
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit India 2026 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.

10:00am IST

Keynote Sessions to be Announced

Tuesday June 16, 2026 10:00am - 12:00pm IST

Jasmine 2 (Third Floor)

Tuesday June 16, 2026 10:00am - 12:00pm IST
Jasmine 2 (Third Floor)

Keynote Sessions

2:00pm IST

Hardening and Scaling Open Agentic Infrastructure With MCP - Hema Veeradhi, Red Hat

Tuesday June 16, 2026 2:00pm - 2:40pm IST

Jasmine 2 (Third Floor)

AI agents are often limited by proprietary "plugin" silos and bespoke integrations. The Model Context Protocol (MCP) offers a universal interface to break these walls, but moving from local scripts to enterprise-scale introduces Day 2 operational hurdles. How do we discover tool-servers in a dynamic cluster? How do we secure the bridge between LLM reasoning and system execution?

This session presents a technical blueprint for operationalizing MCP within a sovereign, open source stack. We move beyond basic connectivity to address 3 core pillars:
1) Dynamic Discovery: Implementing cloud-native service discovery so agents can dynamically negotiate capabilities with ephemeral MCP servers.
2) Zero-Trust Security: Hardening the "Reasoning-to-Execution" path with fine-grained authorization and audit trails to prevent privilege escalation.
3) Full-Stack Observability: Using OpenTelemetry to bridge the gap between model thinking and backend execution, pinpointing failures in production pipelines.

Attendees will leave with a roadmap for building a modular, interoperable agentic infrastructure, ensuring the future of AI remains open and auditable.

Speakers

Hema Veeradhi

Principal Data Scientist, Red Hat

Hema Veeradhi is a Principal Data Scientist working in the Emerging Technologies team part of the office of the CTO at Red Hat. Her work primarily focuses on implementing innovative open AI and machine learning solutions to help solve business and engineering problems. Hema is a staunch... Read More →

Tuesday June 16, 2026 2:00pm - 2:40pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Intermediate

2:50pm IST

Keep AI on Track: Guardrails + OpenTelemetry Observability - Prabal Rakshit, Infosys Technologies

Tuesday June 16, 2026 2:50pm - 3:30pm IST

Jasmine 2 (Third Floor)

Robust guardrails are a foundational requirement for preparing AI agents for enterprise‑grade deployment. They ensure that agents consistently adhere to organizational standards, policies, and ethical expectations.

OpenTelemetry provides a vendor‑agnostic, standards‑based framework for observing and validating guardrail behavior at runtime. Its unified APIs and emerging generative AI semantic conventions enable organizations to safely instrument guardrail logic, eliminate silent failures, and capture valuable telemetry across decision points.

This session explores the role of guardrails across the entire AI stack, including data layers, infrastructure, orchestration components, and LLMs themselves. We demonstrate how open‑source frameworks such as NVIDIA NeMo Guardrails or OpenLIT can be used to implement production‑ready guardrail mechanisms. Finally, we show how key guardrail metrics such as pass/fail rates, top violation categories, and latency impact can be instrumented using OpenTelemetry and visualized through enterprise observability backends like Dynatrace or Grafana.

Speakers

Prabal Rakshit

Principal Technology Architect, Infosys Technologies

Prabal is an architect with experience in cloud first integration and application development. He has been responsible for collaborating with clients to define a solution roadmap to build scalable and resilient cloud native solutions. Areas of interest include Spring Boot, Kubernetes... Read More →

Tuesday June 16, 2026 2:50pm - 3:30pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Any

3:40pm IST

Trust, but Sandbox: Securing AI Agents in Kubernetes - Sudhanshu Prajapati, Improving & Prateek Mishra, Founda Health

Tuesday June 16, 2026 3:40pm - 4:20pm IST

Jasmine 2 (Third Floor)

You wake up, open X, and see the post: new model just dropped. By the time you finish your coffee, it’s installed, pointed at your repo, and already making “helpful” suggestions. It works. It feels safe. But what did you actually just hand over access to, and how would you even notice if it crossed a line?

In this talk, we’ll unpack why testing every new AI model or coding assistant can quietly introduce serious security risks. Using real examples inspired by incidents like OpenClaw, we’ll show how AI systems can access internal data, influence code paths, and create vulnerabilities without ever asking for permission.

We’ll discuss why experimentation without guardrails can bypass existing security controls and normalize unsafe patterns. Most importantly, we’ll focus on what teams can do instead. The session will include a live walkthrough using the Kubernetes agent-sandbox project to demonstrate how AI agents can be isolated, sandboxed, and constrained with clear boundaries.
By the end, attendees will leave with practical approaches to evaluate AI tools safely, apply guardrails, and enable innovation without putting code or data at risk.

Speakers

Sudhanshu Prajapati

Senior Developer Advocate | AI Leader | Open Source Contributor | CNCG Organizer, Improving

Sudhanshu Prajapati is a data and backend engineer turned developer advocate with over 5 years of experience, specializing in cloud-native technologies and distributed systems. He writes technical blogs, docs, and videos to help teams adopt/build tooling around cloud native and AI... Read More →

Prateek Mishra

Cloud Engineer, Founda Health

Cloud Engineer at Founda Health. I spent the last 5 years at Atlan, starting as an intern and leaving as an SDE-II, focused on keeping cloud systems fast, scalable, and secure.

Tuesday June 16, 2026 3:40pm - 4:20pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Intermediate

4:50pm IST

How To Tame Your Agents? - Devidas Jadhav, Vertiv

Tuesday June 16, 2026 4:50pm - 5:30pm IST

Jasmine 2 (Third Floor)

As a developers, we use AI for our tasks. but there are stages.
1. user of web. copy paste code.
2. opencode calude code users basic.
3. using system proimpt PRD driven developement.
4. adding MCP server/ Skills.
5. agentic tools pipelines (code-rabbit)
6. AI Dark factories (gas town)

I have grown from stage 1 to exploring stage 6. creating projects has became trivial with improved models.

Realising tools are there to be tamed but we still need to keep some gaurdrails.

Session will give chronological order how I have grown and How will I develop same project in all stages. using embedded systems example using modbus mcp as well as playwright mcp. in agent.

More over I want to put across the point although AI will make few roles redundant but it will make so many of newer role. How your domain knowledge will help you deliver same projects way faster. passing all minial tasks to AI and perform architectural and review tasks.

Helping AI to write code and Help it to test and fix errors if any. avoiding overfitting.

I will be sharing my personal journey and show How can we achive using FOSS agentic tools for perfect autonomous software facotries.

Speakers

Devidas Jadhav

Senior Software Engineer, Vertiv

I have worked mainly Embeeded Linux. Alumni of CDAC Acts. OpenWrt, Android BSP, OpenBSP and many OSS used in my work. Has been passinate contributor to stackoverflow answering quenstion it the domain of Linux. Avid interst in AI and LLM. Working on implementing Redfish MCP from scratch... Read More →

Tuesday June 16, 2026 4:50pm - 5:30pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Intermediate

5:40pm IST

Scientific Machine Learning With NVIDIA PhysicsNeMo - Aniket Kulkarni & Samudyata Minasandra, Curlscape

Tuesday June 16, 2026 5:40pm - 6:20pm IST

Jasmine 2 (Third Floor)

Predicting how air flows and heat distributes through a physical product is essential for product feasibility studies, performance analysis etc. But it takes hours to days per design variant. You model the geometry, generate a mesh, set up boundary conditions, run the solver, post-process the results. The bigger issue is the back-and-forth between the designer and the simulation engineer. Multiply that by the dozens to hundreds of variants you need to explore a design space, and you get missed deadlines, stale questions, and engineering time spent waiting instead of thinking.
This talk covers usage of OpenFOAM to generate parametric training datasets across geometric and flow parameters with Latin Hypercube Sampling, then train a surrogate model using NVIDIA's PhysicsNeMo framework and its DoMINO (Deep Operator Network for Multi-physics) architecture. DoMINO encodes 3D geometry as a signed distance field, combines it with local surface features, and predicts pressure, temperature, and velocity directly on the part surface in a single forward pass, replacing the entire simulation chain. We'll go through how DoMINO works and why it fits this class of problems.

Speakers

Aniket Kulkarni

Founder, Curlscape

Aniket Kulkarni is an experienced AI leader, entrepreneur, and technologist with expertise in AI; specifically AI Agents using OSS, open source small language models. Aniket is passionate about exploring technology for creating efficient, scalable, and accessible AI solutions that... Read More →

Samudyata Minasandra

Generative AI intern at Curlscape, Curlscape

I’m a Computer Science Engineering undergraduate and Generative AI intern at Curlscape working on scientific machine learning and deep learning. My work spans surrogate modeling for physical systems, operator learning, and building ML pipelines for real-world problems. Recently... Read More →

Tuesday June 16, 2026 5:40pm - 6:20pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Advanced

6:30pm IST

Running On-Device AI With Qualcomm AI Engine Using LiteRT & ExecuTorch - Kartikey Rawat, Qualcomm

Tuesday June 16, 2026 6:30pm - 7:10pm IST

Jasmine 2 (Third Floor)

Learn how to run real AI models fully on-device using Qualcomm’s AI Engine with LiteRT and ExecuTorch. This talk covers architecture, deployment pipelines, performance tuning on NPUs, and real demos showing how to achieve fast, private, low-latency inference on modern AI PCs and mobile devices.

Speakers

Kartikey Rawat

Senior Developer Advocate, Qualcomm

Senior Developer Advocate at Qualcomm| Google Developer Expert in AI and Google Cloud

Tuesday June 16, 2026 6:30pm - 7:10pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Any

10:00am IST

Keynote Sessions to be Announced

Wednesday June 17, 2026 10:00am - 11:30am IST

Jasmine 2 (Third Floor)

Wednesday June 17, 2026 10:00am - 11:30am IST
Jasmine 2 (Third Floor)

Keynote Sessions

12:50pm IST

Democratizing Grid Intelligence for Developing Nations Through Linux-open-source Infrastructure - Dr. Satabdy Jena, Shell India Markets Pvt. Ltd. & Dr. Nikita Rao, IIT Guwahati

Wednesday June 17, 2026 12:50pm - 1:30pm IST

Jasmine 2 (Third Floor)

Developing countries face increasing renewable integration, ageing power grid infrastructure and dependence on proprietary energy management systems. This session presents an open, Linux‑powered blueprint for future-ready power grids built entirely on FOSS principles. Aligned with Shell’s inner‑source philosophy, the approach demonstrates how shared innovation, standardized interfaces and reusable components accelerate scalable grid intelligence. Leveraging the LF Energy ecosystem—extending critical modules for load forecasting, system‑state estimation, load flow, voltage control and fault restoration for electric power grids—the architecture shows how community‑driven development reduces vendor lock‑in, lowers deployment costs and enables rapid iteration. For emerging economies such as India, this model illustrates how open collaboration strengthens energy resilience while advancing secure and efficient digital infrastructure to support long‑term energy transition goals.

Speakers

Dr. Satabdy Jena

Shell India Markets Pvt. Ltd.

Satabdy Jena completed her PhD in Electrical engineering (Power Systems) from IIT ROORKEE in 2023. Post this , she joined Shell Technology Centre Bangalore as a Power Systems Modelling Researcher. Her broader domain of work and research interests include microgrids,
control systems design, Electrolysers integration, e-mobility, Grid Automation, Techno-commercial analysis
... Read More →

Dr. Nikita Ramachandra

Postdoctoral Fellow, IIT Guwahati

Dr. Nikita Ramachandra is a Visvesvaraya Postdoctoral Fellow at IIT Guwahati and a researcher in power systems and smart grid technologies. She previously served as a Project Officer at IIT Madras, where she contributed to the development of advanced grid automation functionalities using a microservices... Read More →

Wednesday June 17, 2026 12:50pm - 1:30pm IST
Jasmine 2 (Third Floor)

Linux for Emerging Countries

Audience Experience Level Intermediate

1:40pm IST

Syzbot To Mainline: How I Merged 21 Kernel Patches as a First-Time Contributor - Deepanshu Kartikey, Clickpost

Wednesday June 17, 2026 1:40pm - 2:20pm IST

Jasmine 2 (Third Floor)

The Linux kernel can feel impenetrable to newcomers — millions of lines of code and a mailing-list workflow unlike anything else in open source. But what if there was a repeatable, beginner-friendly path in?
During my LFX Mentorship (Fall 2025), which I successfully graduated from, I merged 21 patches across 15+ kernel subsystems — including ext4, gfs2, btrfs, ocfs2, f2fs, mm, tracing, networking, and BPF — all using syzbot bug reports as my starting point.
This lightning talk distills that experience into a practical playbook for first-time contributors:

Finding your first bug: navigating the syzbot dashboard and picking approachable reports like memory leaks and missing validations.
Understanding the bug: reading KASAN/KMSAN reports, tracing call stacks, and using git blame.
Writing the fix: structuring kernel patches with good commit messages following kernel conventions.
Surviving code review: handling v2/v3 revisions and learning from maintainer feedback.

If you have ever wanted to contribute to the kernel but did not know where to start, this talk gives you a concrete, battle-tested roadmap.

Speakers

Deepanshu Kartikey

Performance Engineer, Clickpost

Deepanshu Kartikey is a Linux kernel developer with patches merged across BPF, networking, ext4, and memory management subsystems. His contributions have been reviewed by maintainers including Alexei Starovoitov and Theodore Ts'o. He specializes in eBPF-based observability, building... Read More →

Wednesday June 17, 2026 1:40pm - 2:20pm IST
Jasmine 2 (Third Floor)

Linux for Emerging Countries

Audience Experience Level Beginner

3:35pm IST

The Process of Exploration in AI Research: A Researcher’s Perspective - Bibekananda Hati, ExperQuick.org

Wednesday June 17, 2026 3:35pm - 4:15pm IST

Jasmine 2 (Third Floor)

AI research is often portrayed as breakthroughs driven by larger models and more compute. In reality, it is an iterative process shaped by uncertainty, failed hypotheses, and refinement. When unstructured, this exploration leads to wasted compute, irreproducible results, and opaque decision-making.

This talk examines AI exploration from a researcher’s perspective, focusing on responsibility and sustainability. From hypothesis formation to experiment design and model comparison, we explore how structured experimentation enables clearer reasoning and accountable research practices.

A central theme is understanding the behavior of every component of an experiment through systematic testing. Models, data pipelines, loss functions, optimization strategies, and training loops interact in complex ways. By isolating and analyzing these components deliberately, researchers can reduce redundant experimentation, improve transparency, and make more responsible use of computational resources.

Attendees will gain practical principles for building reproducible, sustainable, and ethically grounded AI research workflows in open ecosystems.

Speakers

Bibekananda Hati

Founder & CEO, ExperQuick.org

I hold an MSc in Data Science. My journey began in my first semester while building PyTorchLabFlow, which later became generalized as PyLabFlow. I recently founded, ExperQuick.org, around it to support researchers across domains.

oss in26 ppt bbek pptx

Wednesday June 17, 2026 3:35pm - 4:15pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Intermediate

4:25pm IST

Confidently Wrong: When AI Cannot Catch Its Own Bugs - Shailja Thakur, IBM Research, Bangalore

Wednesday June 17, 2026 4:25pm - 5:05pm IST

Jasmine 2 (Third Floor)

AI systems handle complex reasoning tasks with fluency, yet consistently fail at simple logic — arithmetic, timezone conversions, unit mismatches — with confidence. The problem deepens when AI agents injest AI-generated code/text: the generator and verifier share the same training distribution, and often the same blind spots. A model that writes a wrong timezone conversion will just as confidently verify it as correct. The error is invisible to both.
This talk presents concrete examples and an empirical study of these shared failure modes. We show which categories of errors are most prone to this — where they silently pass both generation and verification — and show practical approaches to break the symmetry using deterministic validation layers that catch what models miss.

Speakers

Shailja Thakur

Research Scientist, IBM Research, Bangalore

I specialize in Large Language models for code, reasoning, alignment, and agentic harness architecture. Her work focuses on building efficient, reliable, and transparent AI system with a particular emphasis on production-grade design automation and safety. I hold a PhD from University... Read More →

Wednesday June 17, 2026 4:25pm - 5:05pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Any

5:15pm IST

Writing for Machines: How To Capture Your Project's "Vibe" and Survive AI Slop - Kaushlendra Pratap Singh & Shaheem Azmal M MD, Siemens

Wednesday June 17, 2026 5:15pm - 5:55pm IST

Jasmine 2 (Third Floor)

Vibe coding is the latest buzz - the practice of defining your intent and letting AI handle the syntax. But are you doing it right to be the 10x developer, or still struggling with the AI Slop? Open source is currently the battleground for this transition, drowning in "AI Slop" and "AI Pressure".

The problem isn't isolated with the AI capabilities; our outdated developer mindset is to be blamed too. We are still treating syntax as the primary asset and writing documentation for human consumption.

We are introducing the new paradigm: In the age of vibe coding, code is a use-and-throw commodity. The true IP of your project is the context, the historical decisions, the constraints, and unwritten rules.

In this session, lets explore how to stop fighting AI agents buy designing for them. We will move beyond the traditional "human-in-the-loop" defense and embrace a new reality of Context Engineers.

Key Takeaways
* Understand the mechanics of AI-assisted coding.
* Why source code is becoming a disposable commodity, and the project context is the new asset.
* Actionable strategies to help AI understand your project's knowledge base.
* How to adapt TDD to validate AI intent.

Speakers

Shaheem Azmal M MD

Technology Expert, OSS Maintainer, Siemens

Kaushlendra Pratap Singh

Lead Research Engineer, Siemens

Kaushlendra Pratap, a Lead Research Professional at Siemens and a passionate advocate for open-source software. With nearly four years of experience in semantic web, license compliance, and machine learning, he has played a key role in contributing to and maintaining tools like FOSSology... Read More →

Wednesday June 17, 2026 5:15pm - 5:55pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Any

6:25pm IST

JSON Wastes 60% of Your AI-LLM Tokens. TOON Fixes That - Vitthal Mirji

Wednesday June 17, 2026 6:25pm - 7:05pm IST

Jasmine 2 (Third Floor)

Every token sent to an LLM costs money. When you serialize data as JSON for a prompt, you pay for repeated field names, extra braces, and structural noise on every single row. For large datasets that overhead runs to 40-60% of your token bill & it adds nothing useful to the prompt.

TOON (Token-Oriented Object Notation) is a compact, human-readable format built specifically for LLM prompts. It writes column headers once and streams data as plain rows, similar to CSV, but with full support for nesting, arrays, and schema markers. The result is 40-60% fewer tokens with measurably better LLM accuracy: 73.9% one-shot vs JSON's 69.7% on tabular tasks.

This talk covers the TOON format from the ground up: why it exists, how it encodes data, when it wins over JSON and when it does not, and how to use it in real LLM prompts today.

Finally we walk through the toon4s-spark integration, connecting Apache Spark and Databricks to TOON and streaming patterns on Delta Lake.

You will leave knowing exactly how to cut LLM prompt costs, with a format and library you can adopt from any JVM stack today.

Check-
https://github.com/com-vitthalmirji/toon4s
https://toonformat.dev/

Speakers

Vitthal Mirji

Staff Software Engineer - Data platforms

Vitthal is a Staff Data Engineer and Software Architect with over 12 years of experience in designing scalable data pipelines, building AI-driven systems, and translating complex business needs into robust technical architecture. He holds deep expertise in data engineering, distributed... Read More →

Wednesday June 17, 2026 6:25pm - 7:05pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Intermediate

7:15pm IST

Beyond Static Benchmarks: Chaos Based AgentCert Evaluation for Real World AI Agents - Saramma George & Suganya Selvaraj, Chetana Amancharla & Praveen Kumar Kalapatapu, Infosys; Deepak Sharma, Microsoft

Wednesday June 17, 2026 7:15pm - 7:55pm IST

Jasmine 2 (Third Floor)

Current evaluation methods for AI agents, which depend on static benchmarks, are in adequate for real-world systems. This session reveals why accuracy-centric evaluations create a dangerous illusion of readiness and how real systems—shifting APIs, incomplete signals, tool failures, cascading dependencies, and environment drift—expose brittleness that benchmarks never measure. We introduce and demonstrate a chaos engineering driven AgentCert approach as an open source project, developed through a collaborative effort of Infosys and Microsoft, that evaluates agents the way real infrastructure tests resilience: by injecting controlled faults, observing recovery behavior, and measuring adaptation under stress. Participants will learn how scenario-based fault models, workload-coupled tests, and observability-rich metrics uncover latent weaknesses and emergent behaviors. The session presents a practical, open, and repeatable framework for certifying agents on robustness, not just correctness—empowering teams to build AI agents that remain stable, safe, and dependable when reality gets messy. See https://github.com/AgentCert for more details.

Speakers

Saramma George

Senior Technology Architect, Infosys Limited

Senior Technology Architect at Infosys, specializing in engineering innovative production‑grade solutions, agent‑driven automation, and next‑generation SD‑WAN and network platforms. With over 16 years of experience in the IT industry, she has built a distinguished career driving... Read More →

Chetana Amancharla

Leader, Emerging Technologies, Infosys

Chetana Amancharla is a Leader in Emerging Technology at Infosys, where she heads the Applied Research Center for Advanced AI. She focuses on sensing promising technologies, contextualizing them for enterprise use, and driving adoption through applied research and engineering validation... Read More →

Suganya Selvaraj

Senior Consultant, Infosys Limited, Infosys Limited

Senior Consultant at Infosys, specializing in Generative AI and Agentic AI, with over a year of experience in this role. Before joining Infosys, she worked as a Postdoctoral Researcher at Seoul National University for two and a half years, focusing on artificial intelligence. She... Read More →

Deepak Sharma

Principal Architect, Microsoft

Deepak Sharma is a Principal Architect and technology leader with 20+ years shaping how enterprises build and scale intelligent systems. He champions AI‑first, model‑driven and agentic architectures, helping organizations move from experimentation to real‑world impact.

His... Read More →

Praveen Kumar Kalapatapu

Senior Principal Technology Architect, Infosys Ltd

An accomplished and results-oriented technology leader with 24 years of experience in AI, Digital technologies and telecommunications domain. Proven ability to incubate and develop innovative products in AI, Autonomous Network, Cloud, NFV, 5G, and Immersive Media domains.

Wednesday June 17, 2026 7:15pm - 7:55pm IST
Jasmine 2 (Third Floor)

Open AI + Data

Audience Experience Level Any

10:00am IST

2:00pm IST

2:50pm IST

3:40pm IST

4:50pm IST

5:40pm IST

6:30pm IST

10:00am IST

12:50pm IST

1:40pm IST

3:35pm IST

4:25pm IST

5:15pm IST

6:25pm IST

7:15pm IST

Get help with the event