# LlamaIndex Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/llamaindex
> Markdown URL: https://aitinkerers.org/technologies/llamaindex.md
> Technology record last updated: 2026-02-26T09:47:19Z
> Generated: 2026-09-22T07:44:41Z

The leading open-source data framework for building context-augmented AI agents and LLM applications.

LlamaIndex is the core data orchestration framework for connecting large language models (LLMs) to your private or domain-specific data. It operationalizes the Retrieval-Augmented Generation (RAG) pipeline: ingesting data from over 160 sources (APIs, PDFs, SQL databases), structuring it into specialized indices (vector, tree, list), and enabling efficient querying. This process grounds LLM responses in your specific knowledge base, accelerating time-to-production for applications like internal knowledge bases, document Q&A systems, and multi-agent workflows. The framework provides both high-level APIs for quick starts and low-level modular components for advanced customization.

- Official technology site: https://www.llamaindex.ai
- Public AI Tinkerers demos and talks: 12
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building an AI on-call engineer](https://dhaka.aitinkerers.org/talks/rsvp_uOXIA4S8_m8)

I'll be presenting the WIP of Aster, an AI on-call engineer. I'll cover how the product works today and the technical choices behind its architecture.

- Event context: AI Tinkerers Dhaka 2nd Meetup: Dhaka Builds with AI! — 2026-02-07 — Dhaka
- Public talk page: https://dhaka.aitinkerers.org/talks/rsvp_uOXIA4S8_m8

### [Giving AI Agents access to the mobile domain](https://sf.aitinkerers.org/talks/rsvp_eL_bTsbknUM)

AI Agent have been locked out of the mobile domain for too long. But they can finally act and mobile phones (especially Android) now to do all kinds of automations. With Droidrun you can automate every mobile app there is by providing the devtools to automate your own phone or scale your Automations with our Cloud API. I will present the cli and framework for a local phone and show how the cloud version look like.

- Event context: AI Infra Jam: Demos That Weren’t Possible Two Months Ago — 2025-09-25 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_eL_bTsbknUM

### [Fullstack Agents with the Vibe Coding Server](https://sf.aitinkerers.org/talks/rsvp_mDjnO--35R0)

We will show how to use a vibe coding server to code 3 fullstack agent apps in under 5 minutes. We will take 30 seconds to set up the Cursor environment with optimized MCP servers for different parts of the stack (LlamaIndex for the agent, CopilotKit for the frontend, Composio for tools). We will take audience requests for the use-case and UI style, and we will build 3 working fullstack agent apps in the remaining 4 minutes.

- Event context: Coding Agents Stack Share — 2025-09-11 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_mDjnO--35R0

### [Beyond RAGAS: Advanced Evaluation Frameworks for RAG and Agent Natural Language Outputs and Planning](https://seattle.aitinkerers.org/talks/rsvp_6KP1R-vWtFI)

This hands-on demo will introduce practical approaches for comprehensive agent evaluation that go beyond basic RAGAS metrics. We'll explore multi-dimensional evaluation frameworks that combine semantic similarity, factual consistency checking, and novel hallucination detection methods, demonstrated through live coding examples using real-world agent outputs. We will investigate the nuts and bots of RAGAS and where it might fail. We will also trying to understand the fundametal framework to evaluate agent output and planning/reasoning

- Event context: AI Dev Tool Track — Seattle Meetup (Sept 8, 2025) — 2025-09-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_6KP1R-vWtFI

### [From a quick prototype to a continuously learning production system: Composable agents for enterprise workflows](https://seattle.aitinkerers.org/talks/rsvp_PEpbFyNMHMg)

I'll walk through both my process -- of collaboratively prototyping AI Agents with domain experts and then building a working application by composing those agents into an agentic system with guardrails, logging, etc. Most importantly, feedback is captured to allow continuous learning.

- Event context: Summer on the Lake - August Tinkerers Meetup! (Demos, Food, Friends) — 2025-08-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_PEpbFyNMHMg

### [AI in compliance](https://pune.aitinkerers.org/talks/rsvp_iBvsvJNvs6Y)

Compliance is often the slowest—and most frustrating—part of bringing a product to market. While product development has accelerated, meeting standards like ISO 27001 or SOC still takes weeks, delaying customer trust. Our solution brings this timeline down from days to hours by embedding AI into the heart of compliance readiness. In this talk, I’ll walk through the two key user flows in our system: For compliance-ready teams — Users upload their documents and select the compliance framework. Our AI agents collaboratively analyze these proofs against each requirement, reasoning over them with LLMs to identify gaps. For founders new to compliance — A chat interface guides them step-by-step to meet the chosen compliance standard, making the process as simple as onboarding to a new tool. We also address real-time compliance monitoring using MCP (Model Context Protocol) servers that connect to the user’s systems in read-only mode, collecting data, identifying risks, and suggesting fixes. We’re building an execution agent that will apply approved changes automatically. Under the hood, we use: Litellm as an LLM gateway to tap into the latest models (OpenAI GPT-5, Google Gemini 2.5 Pro, Claude, etc.) Langfuse for agent monitoring YAML-based prompt management for maintainability LlamaIndex for document indexing to create a knowledge base from uploaded proofs Our internally built compliance knowledge layer for ISO 27001 & SOC standards ECS, Vercel, Next.js, and FastAPI for serving & UI Attendees will see how LLMs, agent frameworks, and real-time integrations can remove compliance as a blocker, turning it into a continuous, automated process.

- Event context: AI Tinkerers Pune - Meetup — 2025-08-23 — Pune
- Public talk page: https://pune.aitinkerers.org/talks/rsvp_iBvsvJNvs6Y

### [Applying Agentic AI in Construction](https://nashville.aitinkerers.org/talks/rsvp_WpUv_DpQeDI)

I'll show early work on agentic AI that we believe will power entire workflows in construction

- Event context: AI Tinkerers Nashville – June 23rd, 2025 — 2025-06-23 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_WpUv_DpQeDI

### [Real-Time Sentiment Analysis of YouTube Live Chats with LLMs](https://montreal.aitinkerers.org/talks/rsvp_zfsW81aYAMY)

Harnessing the power of Large Language Models (LLMs) to gain instant insights into the emotional tone of YouTube Live Chat conversations as they unfold. This demo provides real-time sentiment analysis, enabling a deeper understanding of audience reactions and engagement during live streams.  

- Event context: AI Tinkerers Montreal - May 2025 Meetup at LightSpeed — 2025-05-07 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_zfsW81aYAMY

### [RAFT (Retrieval Augmented Fine Running) for medical apliccation](https://medellin.aitinkerers.org/talks/rsvp_lz7InP48m7I)

Implementation of a new paradigm named RAFT, thats the combination between RAG and Supervised fine tuning. The demo is for a real use case applied for a inmunotherapy cancer

- Event context: AI Tinkerers Medellín #10 - 26 de Febrero 2025 — 2025-02-26 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_lz7InP48m7I

### [Customer name consolidation](https://dubai.aitinkerers.org/talks/rsvp_4QVaajrpwvo)

Every corporation with many branches all over the world needs to consolidate customer names created by employees from companies in different countries. This requires consolidating the names based on the similarity of names and retrieving the children subsidiaries of the same group. For example, National Oil well Varco child subsidiary is DistributingNow. Such names need to be consolidated under one parent group to streamline Business reports required by stakeholders.

- Event context: AI Tinkerers - Dubai Meetup #4 (January) — 2025-01-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_4QVaajrpwvo

### [Founder](https://seattle.aitinkerers.org/talks/rsvp_vgYWT8SpVmE)

ChatBees is a cutting-edge Serverless Platform powering your LLM Apps! ChatBees provides very simple APIs, enabling you to craft a LLM app (Semantic Search, Q&A, Summary and more) for your knowledge base in mere minutes. Constructed from the ground up with a serverless architecture, ChatBees automatically adapts to your workloads, eliminating any management concerns and ensuring you are only billed for your actual usage. Furthermore, ChatBees prioritizes security by implementing robust features such as Role-based Access Control (RBAC), End-to-End encryption, and Key Management, guaranteeing the protection of your data and communications.

- Event context: AI Tinkerers Seattle - February 2024 Meetup — 2024-02-29 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_vgYWT8SpVmE

### [Embedchain - Flask for LLM powered bots](https://sf.aitinkerers.org/talks/rsvp_-gevJ9M6hTI)

Embedchain(3.8K GitHub stars, 750 forks) is a simple framework to create LLM powered bots. Problem: Developers want to create ChatGPT like bots over their continuously updating data sets, but most of them are struggling to achieve good results. Developers face following problems: * Given a data set, how to chunk, which embedding model and vector database to use * How to retrieve relevant documents and what retrieval strategy to apply (semantic search or lexical or both, metadata filtering, re-ranking, HYDE) * How to create and manage embeddings of dataset which is updating? Langchain and LLamaIndex provide extensive tools to interface with an LLM but they are hard for most software developers to understand and use. Embedchain solution: Python and JS packages to add a dataset and query/chat over it. Built on top of Langchain for quick GTM, Embedchain abstracts out: • Loading, chunking, creating vectors and storing in a vector database • Query formation and document retrieval strategies • Creating and managing embeddings. https://embedchain.ai

- Event context: 🤖🔄🧠 AI Tinkerers SF - August Meetup — 2023-08-10 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_-gevJ9M6hTI

## Related Technologies

- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Agentic RAG](https://aitinkerers.org/technologies/agentic-rag) ([Markdown](https://aitinkerers.org/technologies/agentic-rag.md)) — 3 public demos
- [Agno](https://aitinkerers.org/technologies/agno) ([Markdown](https://aitinkerers.org/technologies/agno.md)) — 1 public demo
- [Android Accessibility API](https://aitinkerers.org/technologies/android-accessibility-api) ([Markdown](https://aitinkerers.org/technologies/android-accessibility-api.md)) — 1 public demo
- [Angular](https://aitinkerers.org/technologies/angular) ([Markdown](https://aitinkerers.org/technologies/angular.md)) — 6 public demos
- [ChromaDB](https://aitinkerers.org/technologies/chromadb) ([Markdown](https://aitinkerers.org/technologies/chromadb.md)) — 10 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [CopilotKit](https://aitinkerers.org/technologies/copilotkit) ([Markdown](https://aitinkerers.org/technologies/copilotkit.md)) — 8 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Discord](https://aitinkerers.org/technologies/discord) ([Markdown](https://aitinkerers.org/technologies/discord.md)) — 10 public demos
- [Docker Compose](https://aitinkerers.org/technologies/docker-compose) ([Markdown](https://aitinkerers.org/technologies/docker-compose.md)) — 5 public demos
- [Droidrun](https://aitinkerers.org/technologies/droidrun) ([Markdown](https://aitinkerers.org/technologies/droidrun.md)) — 1 public demo
- [Embedchain](https://aitinkerers.org/technologies/embedchain) ([Markdown](https://aitinkerers.org/technologies/embedchain.md)) — 1 public demo
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos