Top Builders

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

OpenGPTs

OpenGPTs, powered by LangChain's technology stack, offers developers a versatile framework for harnessing AI capabilities. Leveraging over 60 language models, LangSmith's prompt customization, and a suite of 100+ tools, OpenGPTs provides unparalleled control and flexibility in AI model configurations.

General
AuthorLangChain
RepositoryGitHub - LangChain OpenGPTs
TypeCustomizable AI Model Framework

Framework Overview

OpenGPTs serves as a customizable AI framework, allowing users to fine-tune language models, prompts, tools, vector databases, retrieval algorithms, and chat history databases. This level of control surpasses direct usage of OpenAI, enabling developers to interact with APIs directly and craft tailored user interfaces.

Technology Tutorials

Customization

  • 1. Language Models (LLMs): Select from over 60 LLMs integrated with LangChain. Note the varying prompts required for different models.
  • 2. Prompt Customization: Debug and fine-tune prompts with LangSmith for enhanced accuracy.
  • 3. Tool Integration: Access a diverse suite of 100+ tools provided by LangChain or easily create custom tools.
  • 4. Vector Databases: Choose from 60+ vector database integrations within LangChain.
  • 5. Retrieval Algorithms: Optimize retrieval algorithms based on project requirements.
  • 6. Chat History Databases: Tailor chat history databases to suit specific project needs.

Agent Types (Default):

  1. "GPT 3.5 Turbo"
  2. "GPT 4"
  3. "Azure OpenAI"
  4. "Claude 2"

OpenGPTs' appeal lies in its high level of customization compared to direct usage of OpenAI. Users gain control over language model selection, seamless addition of custom tools, and direct API utilization. Furthermore, developers can craft custom UIs as needed.

Utilize OpenGPTs to harness the power of AI tailored precisely to your project requirements.

For a deeper dive into usage and configuration, refer to the OpenGPTs Documentation.

Edit on GitHub

Langchain OpenGPTs AI technology Hackathon projects

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

Benchmarking Robustness in Agentic RAG Systems

Benchmarking Robustness in Agentic RAG Systems

As AI agents become increasingly integrated into real-world applications, understanding retrieval reliability and preprocessing sensitivity has become a major challenge in Retrieval-Augmented Generation (RAG) systems. Most traditional evaluations focus only on architecture performance while ignoring how preprocessing decisions can significantly affect retrieval robustness and benchmark outcomes. In this project, we built an interactive observability and benchmarking platform for evaluating robustness in Agentic RAG systems. The platform compares Single-Agent and Multi-Agent RAG architectures across SQuAD and HotpotQA benchmarks using Exact Match (EM) and F1 evaluation metrics. Through systematic experiments, we discovered a key insight: preprocessing strategies such as chunking can completely flip benchmark winners. Without chunking, the Single-Agent system slightly outperformed the Multi-Agent system on SQuAD. However, after introducing chunking, the Multi-Agent architecture became significantly more robust under noisy retrieval conditions. To make these behaviors observable, we developed an interactive Streamlit dashboard featuring benchmark comparison analytics, retrieval trace visualization, chunking impact analysis, and failure inspection. One of the core components of the platform is the Retrieval Trace Viewer, which allows users to inspect how Multi-Agent systems rewrite queries, retrieve semantically richer chunks, and improve answer generation step-by-step. We also analyzed common RAG failure modes such as vocabulary mismatch, retrieval pollution, and chunk fragmentation. Our findings demonstrate that retrieval robustness depends not only on architecture design but also heavily on preprocessing strategy and retrieval quality. Technologies used include LangChain, LangGraph, FAISS, HuggingFace Embeddings, Groq LLMs, Streamlit, Plotly, and Python.

env-doctor

env-doctor

🩺 env-doctor Stop wasting expensive GPU hours on environment failures. Have you ever had an ML build fail or rerun expensive training because of a CUDA mismatch? You launch a job on a $30/hr H100 cluster, only to find it crashed 5 minutes in because flash-attn wasn't compiled for your CUDA version or xformers mismatched with torch. Enter env-doctor: a local-first runtime compatibility platform for Python AI/ML workflows. Premise: "If one user faces an environment failure, no other user will ever face it again." 🌟 Why env-doctor? Traditional managers only check if packages can be installed together. env-doctor checks: "Will this stack actually work at runtime on your exact hardware?" We stop OOM errors, silent CUDA fallback slowdowns, and breaking changes before you provision a GPU. Core Features 🛡️ Community Intelligence: Vetted by AI agents (Watsonx Orchestrate) and pushed to a global DB. 🧠 Smart VRAM Estimation: OOM detection accounting for quantization, KV cache, and fragmentation across vllm, transformers, llama.cpp, and tgi. 🚀 Stable Recommendations: Analyzes hardware to recommend rock-solid dependency stacks. 🔍 Deep Checks: Scans files against known ABI conflicts and CUDA mismatches. 🤖 AI Bug Reporting: Captures stack traces and system states to generate new protection rules. ⚡ Quick Start Install env-doctor globally using uv or pip: pip install env-doctor-pypi 1. Sync Database: env-doctor update-db 2. Check Project: env-doctor check requirements.txt 🔴 Critical Issue: torch 2.1.0 and flash-attn 2.5.0 conflict. Will cause segmentation fault. 3. Estimate VRAM: env-doctor vram --model meta-llama/Llama-2-7b-hf --runtime vllm --seq-len 32768 --quant fp16 4. Get Recommendations: env-doctor recommend 🛠️ Supported: vllm, transformers, tgi, deepspeed, tensorrt-llm, llama.cpp, onnxruntime on NVIDIA GPUs (CUDA). (Majority of the code is written by IBM Bob. Thanks Bob!!)

Iroko AI — Enterprise Intelligence for Africa

Iroko AI — Enterprise Intelligence for Africa

Enterprise AI in Africa has a problem. Operations teams at telecoms like MTN Nigeria are drowning in documents — SLA registers, vendor contracts, NCC compliance reports, network incident logs — with no intelligent layer to surface what matters before it becomes a crisis. Iroko AI solves this with a proactive 5-agent intelligence pipeline built on Azure OpenAI and Microsoft Semantic Kernel. The five agents — Watchdog, Researcher, Analyst, Strategist, and Scribe — work in sequence: Watchdog continuously monitors enterprise documents for anomalies and SLA breaches, Researcher retrieves relevant context from Azure AI Search, Analyst synthesizes findings and scores risk from 1 to 10, Strategist generates recommended actions, and Scribe formats the final output. What makes Iroko AI different is the Live Reasoning Chain — a real-time streaming interface that shows every agent step as it happens. Operators watch five agents think, collaborate, and hand off to each other before delivering a final intelligence report. This is not a chatbot. This is enterprise decision support. The platform includes a Network Operations Centre dashboard with a live Nigeria network map showing real tower site health across Lagos, Abuja, Kano, and Port Harcourt. It connects to enterprise data sources including SharePoint, ServiceNow, Slack, and Microsoft Teams. It surfaces proactive alerts without being asked. It maintains full audit trails for regulatory compliance. Built for African telecoms. Grounded in real MTN Nigeria operational data. Powered by Azure OpenAI GPT-5.4, Azure AI Search, and Microsoft Semantic Kernel. This is what enterprise AI looks like when it is built for the problems that actually exist.

AegisNexus AI

AegisNexus AI

AegisNexus AI is a production-style AI governance and adversarial defense platform designed to secure modern AI systems against prompt injection attacks, unsafe instructions, policy violations, and malicious agent behavior. The project combines a FastAPI backend with a cinematic React frontend to create a live operational command center for AI security monitoring and governance simulation. The backend architecture was built with modular FastAPI services and includes: • Real-time prompt threat analysis • Governance guardrails for prompt inspection • Policy enforcement engine • SQLite persistence and audit logging • Telemetry streaming using WebSockets • Threat scoring and response recommendations • Gemini API integration with fallback heuristic analysis • Attack simulation endpoints for testing AI resilience The frontend was designed as a futuristic AI defense interface featuring: • Interactive adversarial simulation sandbox • Real-time telemetry monitoring • Threat visualization dashboards • Incident containment indicators • Live risk score analysis • Dynamic governance metrics • Responsive cyberpunk-inspired UI with Framer Motion animations Users can enter prompts into the simulator to test how the governance engine reacts to malicious or unsafe instructions. The platform evaluates the prompt, assigns a threat level, calculates a risk score, and recommends actions such as BLOCK, REVIEW, or ALLOW. Example attacks include: • Prompt injection attempts • Instruction override attacks • Credential extraction attempts • Jailbreak prompts • Policy bypass requests AegisNexus AI was created to demonstrate how future AI systems can include transparent governance layers, safety orchestration, and adversarial monitoring before deploying autonomous agents into real-world environments.