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.

TRiaD

TRiaD

TRiaD (Threat Intelligence & Automated Defense) is an AI-powered cybersecurity incident response platform developed during the Band of Agents Hackathon 2026. The system leverages a collaborative multi-agent architecture to automate the traditionally time-consuming processes of threat analysis, incident triage, intelligence correlation, and compliance reporting. The platform consists of specialized AI agents working together in a coordinated workflow. Incoming security alerts are processed by an ingestion layer, enriched with contextual threat intelligence, and analyzed through semantic similarity searches using a vector database. The analyst agent investigates indicators of compromise, correlates findings with historical incidents and MITRE ATT&CK techniques, and generates actionable insights. A manager agent then compiles compliance-ready incident reports suitable for security operations centers and organizational stakeholders. TRiaD provides a modern web dashboard with real-time updates, interactive alert monitoring, and automated reporting capabilities. By combining FastAPI, Next.js, ChromaDB, Gemini-powered reasoning, and WebSocket-based communication, the platform demonstrates how autonomous AI agents can significantly accelerate cyber defense operations while maintaining transparency, traceability, and auditability. The project showcases practical applications of agentic AI in cybersecurity, threat intelligence automation, incident response orchestration, and security analytics.

AI Recruitment Platform

AI Recruitment Platform

AI Recruitment Platform is a multi-agent system designed to automate and enhance the job discovery process for software and data professionals. The platform continuously collects job postings from multiple sources, including LinkedIn and staff.am, and processes them through a collaborative network of specialized agents. The system is built around a three-agent architecture. The Ingestion Agent is responsible for crawling, collecting, and normalizing job postings from various online sources. Once jobs are gathered, the Scoring Agent evaluates opportunities based on predefined criteria such as role relevance, skills, location, employment type, and other metadata. Finally, the Recommendation Agent analyzes the ranked opportunities and generates personalized recommendations for users. To demonstrate the agent workflow, the platform includes an interactive dashboard that visualizes the entire pipeline from data ingestion to recommendation generation. Users can monitor crawler activity, view job statistics, inspect processed opportunities, and observe how agents collaborate to transform raw job data into actionable recommendations. The project addresses a common challenge faced by job seekers: discovering relevant opportunities quickly across fragmented platforms. By automating job collection and leveraging agent-based processing, the system significantly reduces manual effort while increasing coverage and relevance. Key features include: • Multi-source job crawling and aggregation • Autonomous multi-agent workflow • Job scoring and ranking engine • Recommendation generation pipeline • Real-time dashboard and monitoring • SQLite-based persistence layer • Smart fallback mechanisms for high availability • Streamlit-powered user interface The platform demonstrates how multi-agent systems can be applied to real-world productivity and career development problems, showcasing autonomous collaboration, workflow orchestration, and practical AI-assisted decision-making.

Syndicate — Self-Improving AI Dev Swarm

Syndicate — Self-Improving AI Dev Swarm

Syndicate is a self-improving multi-agent orchestration platform that transforms software development from isolated AI interactions into visible, compounding collaboration between specialized intelligences. THE PROBLEM: Today's AI coding tools are stateless. They never learn. Planning, coding, reviewing, and deploying are fragmented steps with no shared memory. Every session starts from zero. HOW IT WORKS: Syndicate deploys 6 specialized agents — Nexus (coordinator), Architect (planning), Engineer (coding), Reviewer (adversarial cross-model review), Researcher (context gathering), and QA (validation) — all collaborating through Band rooms with @mention routing. When you submit a task, Nexus dynamically recruits agents based on complexity, orchestrates handoffs, and routes work through a complete lifecycle visible in real-time on the dashboard. WHAT MAKES IT DIFFERENT: • Compound Intelligence — Every task teaches the system. Memory persists. Skills evolve. The 100th task executes 10x better than the 1st. • Multi-Model Adversarial Review — The model that writes code is never the only model that reviews it (Gemini writes, GPT-4o reviews). • Dynamic Topology — Simple fix = 3 agents. Full feature = 7 agents. The swarm scales to task complexity. • Visible Collaboration — Agent-to-agent work isn't hidden. You see who did what, why decisions were made, and how handoffs happened in real-time. • Self-Improvement Loop — After every cycle: extract lessons → update memory → refine agent skills → next cycle is measurably better. THE EXPERIENCE: An immersive 3D dashboard with live agent visualization, real-time event streaming, approval gates for human-in-the-loop control, semantic memory search, and quantified self-improvement metrics — all deployed and callable from your IDE via MCP. Syndicate doesn't just help you code. It grows into your engineering teammate.

BlackBox-Labs --AI Infrastructure & Orchestration

BlackBox-Labs --AI Infrastructure & Orchestration

**BlackBox Labs** is an AI Infrastructure Control Plane designed to make multi-agent AI systems observable, reliable, and manageable. Rather than focusing only on AI-generated responses, it provides the infrastructure needed to orchestrate, monitor, and analyze agent workflows. Built with **Next.js**, **FastAPI**, and **LangGraph**, the platform coordinates three specialized agents: a **Planner** that creates an execution strategy, a **Researcher** that gathers and expands information, and a **Reviewer** that validates and synthesizes the final response. Each stage is independently tracked and monitored throughout execution. The platform includes a **Model Routing Layer** that dynamically routes requests across providers such as **Google Gemini** and **OpenRouter-hosted models**. To improve reliability, BlackBox Labs supports automatic retries, provider fallback mechanisms, timeout protection, and error recovery, allowing workflows to continue even when individual models or providers fail. A core feature of the project is **observability**. Users can inspect execution timelines, monitor agent status, view routing decisions, analyze provider usage, track fallback events, and review execution metadata including runtime, model selections, and success metrics. BlackBox Labs also provides an **analytics layer** with insights into success rates, execution volume, average runtime, provider utilization, fallback frequency, and agent performance trends. In addition to the web dashboard, the platform integrates with **Band.ai** through a custom remote agent, enabling users to access the same orchestration engine from an external collaborative agent environment. By combining multi-agent orchestration, model routing, reliability engineering, observability, analytics, and Band.ai integration, BlackBox Labs demonstrates how AI workflows can be operated as infrastructure systems rather than isolated chatbots.

Vendor Risk Radar

Vendor Risk Radar

Enterprises depend on dozens of third-party vendors, and when one is breached they usually learn from the news - weeks too late. The hardest part isn't a single vendor; modern breaches cascade. One stolen OAuth token (Salesloft-Drift), one compromised identity provider (Okta), one poisoned dependency silently spreads to every connected vendor. Companies have a vendor list but no visibility into the connections between vendors - so they can't answer the question that matters: which of my other vendors are now exposed, and must I act today? Vendor Risk Radar turns the live web into continuous, cited vendor risk intelligence. For each vendor it runs real-time discovery across Google News, breach trackers, CVE feeds, status pages and regulatory portals, extracts structured risk signals with AI, and computes a transparent 0–100 risk score with recency decay - every signal backed by a real source URL, never invented. Our differentiator, Blast Radius, reads recent security incidents across all vendors, automatically discovers the connections between them (shared attacker, OAuth token, identity provider, cross-vendor mention), and clusters them into single incidents. For each it issues a clear verdict—INVESTIGATE / MONITOR / NO ACTION - with reasoning and citations, correctly separating the 4-vendor Salesloft-Drift OAuth cascade from the Okta–Cloudflare identity incident. Built with Bright Data SERP API for live discovery and Web Unlocker to bypass bot-protected breach trackers and trust centers (provable 403→200), plus AI/ML API (Claude) for extraction. A hosted MCP server exposes the data to any AI agent—just ask "Am I exposed to a cascading breach this week?" The stack (FastAPI + React + SQLite) is containerized and deployed live on Hugging Face Spaces, moving third-party risk from reactive headlines to proactive, connection-aware monitoring.

CyberSentinel: AI Threat Intelligence

CyberSentinel: AI Threat Intelligence

CyberSentinel is an intelligent cybersecurity platform designed to combat the growing threat of phishing attacks, malicious websites, and online fraud. The platform combines AI-driven threat analysis, real-time web intelligence, and automated security assessments to help users identify and respond to cyber threats before they cause damage. Users can submit suspicious URLs for analysis, where CyberSentinel performs deep inspection of website characteristics such as login forms, password fields, SSL certificates, domain reputation, typosquatting indicators, redirects, and suspicious content patterns. The collected evidence is processed through an AI-powered analysis engine that generates risk scores, phishing likelihood assessments, technical explanations, and recommended mitigation actions. The platform features an interactive cyber-security dashboard, threat monitoring capabilities, risk visualization, and detailed intelligence reports that transform complex security data into understandable insights. By leveraging modern AI models and automated threat intelligence techniques, CyberSentinel enables faster and more accurate threat detection compared to traditional manual investigation methods. CyberSentinel is designed for security teams, organizations, students, and everyday internet users who need an accessible yet powerful solution for identifying phishing campaigns and malicious web infrastructure. The system is scalable, cloud-deployable, and can be extended to support enterprise threat monitoring, credential leak detection, and automated incident response workflows. Our mission is to make advanced cyber defense accessible to everyone by combining artificial intelligence with practical cybersecurity intelligence.