Harish Kotra
Developer Relations, Hackathons Specialist & A No-Code Educator
Hyderābād, India
Actions
DevX Lead at XO (https://xo.builders) - Launch your autonomous agents in seconds with private infra
Fractional CTO at Forge Alumnus (https://forgealumnus.com & https://hackforge.ai)
Previously was a Developer Advocate at Gaia 🌱 (https://gaianet.ai). I focus on onboarding developers, enterprises create, launch and scale their own AI Agents.
I was a Community Lead for AngelHack, a global company dedicated to Developer Relations and building diverse communities of change makers and innovators worldwide for over 11 years. I am also a passionate advocate for no-code technology and believe in empowering individuals to bring their own ideas to life without coding.
I have helped run some of the best hackathons and developer competitions globally, providing opportunities for developers to showcase their skills and ideas. I have also hosted and ran over 200 hackathons for developers and students across India, Maldives, Sri Lanka, Bangladesh, Pakistan, Dubai, and more countries.
In my spare time, I help entrepreneurs build and automate anything without coding. I create content on YouTube about no-code and help entrepreneurs build their businesses and automate their tasks. I am passionate about using technology to solve real-world problems and make a positive impact on the world.
I have worked with Microsoft, Discover, IBM, AWS, Mastercard, Jina.ai, DataStax, Consensys, Algorand, Celo, Zepeto, and Polkadot, and more in helping with their developer acquisition and developer relations.
I am excited to be part of the tech community and am always looking for new ways to support and empower developers and entrepreneurs.
Links
Badges
Area of Expertise
Topics
Running MCP Fully Local: Private, Offline-Capable Agents with Ollama and Open Models
Over the last few months I've built and shipped 100+ agents in public, many wired into MCP servers running against local models through Ollama, LM Studio, and decentralized open-source inference. A draw.io MCP server driven by Llama 3.2, an Excalidraw MCP integration, a Bright Data MCP briefing agent, all running end-to-end without a single token leaving the host.
This talk is a working engineer's tour of that stack. We'll walk through a minimal local MCP setup (server + client + Ollama) and then dig into the real-world failure modes: tool-selection collapse on 7B models, JSON-schema compliance gaps, capability-negotiation mismatches, and the surprisingly large quality delta between structured-output fine-tunes and general chat models. I'll share the prompt shapes, tool-description patterns, and schema-validation tricks that reliably push small open models from "demo-grade" to "I'd ship this internally."
Attendees will leave with a reference architecture for private MCP, a shortlist of open models that actually handle tool calls well today, and a set of design patterns for MCP servers that degrade gracefully when the client LLM has 8B parameters instead of a trillion.
Clone Yourself with Local LLMs
Master the Retrieval-Augmented Generation (RAG) pipeline for personal data using open-source models, local vector stores, and lightweight tools to achieve “style cloning” without costly fine-tuning.
In this 45-minute hands-on session, you’ll build a self-sovereign AI agent that writes like you - powered by a privacy-first, open-source framework.
We start with Data Sovereignty: learn how to legally export your data (e.g., X/Twitter or LinkedIn archives) and convert JSON or CSV files into a clean “voice corpus.”
Next, explore Voice Vectorization via RAG - embedding your content into a private vector store so your AI “remembers” your style and topics without retraining.
Finally, Deploy the LLM (e.g., Gemma 3) locally and apply prompt engineering to generate authentic, on-topic content: tweets, posts, or emails, in your own voice.
Leave with portable code to run the agent entirely offline: $0 API costs, full privacy, and total control of your digital persona.
100 Agents in 100 Days: Patterns and Anti-Patterns for MCP-Based Multi-Agent Systems
Multi-agent systems on MCP are where most of the interesting architectural questions live: routing, state, retries, coordination, and what happens when any one of N tool calls misbehaves. Most talks on the topic are theoretical. This one is not.
Since early 2026 I've published one new AI agent every day at dailybuild.xyz. Many of them are multi-agent: price-war simulations, research pipelines, a local agent orchestration studio, a recursive research loop, human-in-the-loop travel planners, and a "swarm CFO" with policy-gated spend. Dozens of them plug into MCP servers.
In this session I'll pull out the ten orchestration patterns I now use by default when MCP is in the mix, and the ten I've thrown out. Topics include: why single-agent-with-many-tools usually beats a team of agents until it suddenly doesn't; how to design a router that survives tool-name collisions across multiple MCP servers; state strategies that don't rot; retry and compensation patterns for idempotent vs non-idempotent tools;
Every pattern in the talk is tied to a specific public build with working code, so attendees can go verify, fork, or challenge anything I claim.
OpenSearch with Gaia: Building Next-Gen AI-Driven Search and Analytics Workflows
This session explores how Gaia’s decentralized AI platform integrates with OpenSearch to create scalable, privacy-preserving solutions for semantic search, generative AI applications, and real-time analytics.
In this session, I intend to demonstrate a use case where Gaia’s federated learning models enhance OpenSearch’s vector database capabilities, enabling dynamic personalization and efficient retrieval-augmented generation (RAG) workflows.
Gaia’s AI Framework: How Gaia’s decentralized architecture complements OpenSearch’s ecosystem, particularly in scenarios requiring data privacy and distributed model training (e.g., healthcare or financial analytics).
Demo a RAG Pipeline: Build a real-world demo/example using Gaia’s language models to generate embeddings stored in OpenSearch’s binary vector indexes (new in v2.19), coupled with OpenSearch Flow for automated pipeline configuration.
Community Impact: A look at how this integration supports OpenSearch’s goal of becoming the preferred backend for generative AI while adhering to open governance principles.
MCP Dev Summit Mumbai 2026 Sessionize Event
MCP Dev Summit Bengaluru 2026 Sessionize Event
AI Community Conference - AICO Seoul Sessionize Event
OpenSearchCon India 2025 Sessionize Event
Harish Kotra
Developer Relations, Hackathons Specialist & A No-Code Educator
Hyderābād, India
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top