Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

LlamaIndex: a Data Framework for LLM Applications

LlamaIndex is an open source data framework that allows you to connect custom data sources to large language models (LLMs) like GPT-4, Claude, Cohere LLMs or AI21 Studio. It provides tools for ingesting, indexing, and querying data to build powerful AI applications augmented by your own knowledge.

General
AuthorLlamaIndex
Repositoryhttps://github.com/jerryjliu/llama_index
TypeData framework for LLM applications

Key Features of LlamaIndex

  • Data Ingestion: Easily connect to existing data sources like APIs, documents, databases, etc. and ingest data in various formats.
  • Data Indexing: Store and structure ingested data for optimized retrieval and usage with LLMs. Integrate with vector stores and databases.
  • Query Interface: LlamaIndex provides a simple prompt-based interface to query your indexed data. Ask a question in natural language and get an LLM-powered response augmented with your data.
  • Flexible & Customizable: LlamaIndex is designed to be highly flexible. You can customize data connectors, indices, retrieval, and other components to fit your use case.

How to Get Started with LlamaIndex

LlamaIndex is open source and available on GitHub. Visit the repo to install the Python package, access documentation, guides, examples, and join the community:

AI Tutorials

LlamaIndex Libraries

A curated list of libraries and technologies to help you build great projects with LlamaIndex.

Edit on GitHub

LlamaIndex AI technology page Hackathon projects

Discover innovative solutions crafted with LlamaIndex AI technology page, developed by our community members during our engaging hackathons.

Onus HybridMind: AI Procurement Auditor

Onus HybridMind: AI Procurement Auditor

Enterprise procurement teams are bound by complex vendor contracts containing rebate thresholds, volume discounts, and penalty clauses buried in dense legal documents. Meanwhile, SQL databases hold the transaction records, but no one cross-references them against contract terms at scale. The result is millions in uncollected rebates and compliance gaps going undetected. To solve this, we built HybridMind: an autonomous AI audit agent that bridges structured SQL procurement data and unstructured vendor contracts in real time. It is not a standard RAG chatbot; it is a deterministic, multi-agent auditor built specifically to stop financial leakage. Our backend leverages LlamaIndex Workflows to orchestrate three distinct AI agents powered by Gemini 3.1 Flash Lite. The process begins with the Executor Agent. It converts natural language into strict SQL queries against our Supabase PostgreSQL database while simultaneously querying our ChromaDB vector store for the exact legal clauses. Next, the Verifier Agent takes both data sources and performs logical validation. It cross-references the SQL math against the PDF rules to detect discrepancies, such as verifying if a 12,000 unit purchase correctly triggers a 10,000 unit rebate threshold. Finally, the Chronicler Agent packages the verified finding and broadcasts the financial metrics to our live React dashboard via WebSockets. This architecture ensures transparent reasoning. While standard AI often hallucinates numbers, HybridMind forces the AI to show its raw SQL, explicitly cite its contract clauses, and prove its math. By keeping the frontend stateless and the backend firmly grounded in dual-silo retrieval, nothing is hidden behind a black box. Ultimately, HybridMind turns silent leakage into documented liability.

Sprint-to-Code Pipeline

Sprint-to-Code Pipeline

Modern software teams waste hours translating tickets into actionable engineering work - manually hunting through codebases, guessing which files need changing, and writing boilerplate scaffold. This tool eliminates that entirely. Given a ticket title and description, the system generates vector embeddings of the input, semantically searches the target GitHub repository's codebase (pre-indexed via chunk-level embeddings), and retrieves only the files and code blocks with the highest contextual relevance. No full-repo dumps. No irrelevant noise. Just the exact context the model needs. That enriched context -ticket + relevant code - is fed to an LLM which outputs three things: a structured subtask breakdown that maps work to logical engineering units, a file modification plan that names exact files, functions, and the nature of each change, and working code scaffolds pre-wired to the existing codebase conventions, imports, and patterns. The output isn't a chat response. It's a draft GitHub Pull Request - automatically created against the target repo with a structured description, the subtask checklist, and scaffold code committed to a feature branch. Engineers receive a PR that's already 40–60% complete and contextually accurate, not a blank branch and a vague ticket. The system is designed for real codebases: it handles chunking strategies for large files, respects token budget constraints when assembling context, and uses reranking to prioritize the most semantically dense matches before injection. The result is faster sprint execution, fewer "where do I even start" moments, and a tighter loop between product requirements and shipped code.

Agentic Security & Observability Platform

Agentic Security & Observability Platform

Governance.AI is an agentic security and observability platform designed for autonomous AI systems and multi-agent workflows. As AI agents become more integrated into real-world products, most systems still operate with very little visibility, monitoring, or governance. We wanted to build infrastructure that helps developers understand and control how AI systems behave internally. The platform introduces a centralized governance layer between users and AI agents. Instead of acting like a simple chatbot wrapper, Governance.AI continuously monitors workflows, traces execution paths, analyzes risky behavior, and enforces governance policies before actions are executed. Core capabilities include: Risk Detection & Prompt Analysis Policy Enforcement & Access Control Agent Monitoring & Observability Audit Trails & Explainability Red-Team Testing & Unsafe Prompt Detection Real-Time Governance Workflows The platform is built using a modular FastAPI service architecture connected through a scalable API gateway. We integrated LangSmith for tracing and observability, Auth0 for authentication, Neon PostgreSQL for infrastructure data, and a real enterprise-style dashboard with live workflows, analytics, traces, and governance events. Governance.AI can be integrated using: Python SDK REST APIs Gateway-based integrations Developers can test governance services directly from the dashboard, inspect traces, monitor workflows, and integrate Governance.AI into their own AI systems using SDKs or APIs. One important aspect of this project is that we intentionally avoided building a purely mocked prototype. Our focus was building a realistic developer infrastructure platform that could evolve into a production-grade governance layer for future AI ecosystems. We believe governance, trust, and observability will become foundational infrastructure for autonomous AI systems, similar to how monitoring and security became essential for cloud computing.

RepoPilot

RepoPilot

RepoPilot is an AI-powered developer onboarding platform that helps developers quickly understand complex codebases. Modern repositories are often large and difficult to navigate, making onboarding slow and confusing. RepoPilot solves this by turning repositories into an interactive, AI-driven learning experience. It connects directly to GitHub and performs deep analysis of project structure, architecture, dependencies, modules, APIs, workflows, and runtime behavior. Instead of manually exploring code, developers get structured insights and AI-generated explanations. A key feature is its Codebase Q&A Assistant, where users can ask questions in natural language and receive context-aware answers based on the repository. It also provides automatic code explanations that simplify complex modules while still supporting advanced detail. RepoPilot includes project structure visualization and dependency mapping, helping developers understand how files, services, and modules connect and how data flows through the system. It also offers runtime flow tracing to visualize execution paths step by step. A Smart Onboarding Flow generates guided learning paths based on repository complexity, ensuring developers explore important components in the right order. The platform supports Beginner and Professional modes to adjust explanation depth. Built with Next.js, React, TypeScript, Tailwind CSS, and GitHub APIs, RepoPilot reduces onboarding time and improves developer productivity by making complex systems easier to understand.

AP Sentinal

AP Sentinal

AP Sentinel is a working prototype of a safety layer for procurement and accounts payable agents. Enterprise agents are useful when they can call tools: look up vendors, check purchase orders, stage payments, update vendor records, or send messages. But invoices, PDFs, and supplier emails are untrusted inputs. They can contain malicious instructions that try to push an agent outside its intended workflow, such as turning an invoice review task into a payment release or vendor-data export. AP Sentinel sits between the agent and its tools. Before any tool runs, it checks whether the proposed action matches the trusted workflow intent. Safe read-only tools like invoice extraction, vendor lookup, and purchase-order lookup are allowed. Risky actions like releasing payments, exporting vendor data, updating bank details, or sending external emails are blocked or sent to human review. The prototype includes file upload and parsing, LlamaParse OCR support for scanned invoices, optional Gemini function calling, a deterministic local agent mode for reliable demos, SQLite-backed sandbox tools, policy reason codes, a hash-chained audit log, Lobster Trap-style security event envelopes, and a regression suite covering safe and malicious scenarios. The finance tools are sandboxed for safety: no real money moves and no real ERP or email system is contacted. The goal is to demonstrate the runtime control layer enterprises need before allowing AI agents to operate inside payment, procurement, and vendor-management workflows.