Browse applications built on Langchain OpenGPTs technology. Explore PoC and MVP applications created by our community and discover innovative use cases for Langchain OpenGPTs technology.
An automated BI agent that summarizes complex datasets and generates presentation-ready layouts, laying the groundwork for video-driven automated data reporting.
A local DistilBERT binary router sends each query to the cheapest suitable Fireworks model, preserving answer quality while using zero routing tokens across eight task categories.
AI agent that analyzes video clips and automatically generates accurate captions in formal, sarcastic, humorous tech, and humorous non-tech styles using computer vision and LLMs.
The only video captioning studio that QCs itself. Gemma locks the facts, then writes four calibrated voices — formal, sarcastic, tech & non-tech humor — each caption pre-judged for accuracy and tone before you see it. Gemma-first on Fireworks AI.
An AI-powered video captioning agent that analyzes videos, understands scene context using multimodal AI, and generates accurate captions in multiple styles including formal, sarcastic, and humorous outputs.
AI-powered video captioning platform analyzes videos and automatically generates accurate captions in four distinct styles. Built with React, FastAPI, Docker, and AMD Fireworks AI, it delivers fast, creative captions through an intuitive web interface.
A hybrid token-efficient routing agent that optimizes operational costs by dynamically shifting low-compute tasks to a local Qwen-1.5B model while cascading complex tasks to enterprise remote models using an aggressive token starvation protocol.
Hacienda is an autonomous video-captioning agent. It samples keyframes, builds a factual scene analysis with a vision model, then writes four distinct captions per clip - formal, sarcastic, tech humor, everyday humor - in Docker, minutes per batch.
Local-first AI agent that scans CUDA-heavy GitHub repos, pinpoints AMD ROCm migration blockers with file-level evidence, generates risk-scored patch artifacts using a local Ollama model, and exports verified, GitHub-ready review bundles. No cloud API.
OneMind AI OS is an intelligent multi-agent workspace that helps users research complex topics, design software architectures, and validate startup ideas through specialized AI agents powered by Fireworks AI.
An AI agent where lightweight rules and semantic similarity vote together on how hard a question is — confident cases get answered directly, uncertain ones make the local model prove itself twice before trusting it.
TRiaD (Threat Intelligence & Automated Defense) is a multi-agent cybersecurity platform that automates incident triage, threat intelligence analysis, and compliance reporting using AI agents, semantic search, and real-time alert processing.
A multi-agent AI recruitment platform that crawls jobs from multiple sources, ranks opportunities through specialized agents, and delivers personalized recommendations via an interactive dashboard for faster job discovery.
A multi-agent developer platform where 6 specialized AI agents collaborate through Band rooms, learn from every task, and compound intelligence across sessions — turning planning, coding, and reviewing into a visible swarm conversation.
BlackBox Labs is an AI infrastructure control plane that orchestrates multi-agent workflows with model routing, fallback recovery, observability, analytics, and Band.ai integration.
Continuous, cited third-party vendor risk intelligence from the live web. Our Blast Radius engine detects when one breach cascades across connected vendors and flags exactly who to investigate - powered by Bright Data SERP, Web Unlocker + AI.
CyberSentinel is an AI-powered cybersecurity platform that detects phishing websites, analyzes threat indicators in real time, and generates actionable threat intelligence to help users identify and mitigate online threats.
Autonomous market research agent utilizing Gemini 3.5 Flash and Streamlit. It executes a parallel ReAct loop using Bright Data's SERP & Web Unlocker APIs to search, scrape, and compile structured company dossiers from live web data.
An interactive observability and benchmarking platform for evaluating retrieval robustness in Single-Agent and Multi-Agent RAG systems across SQuAD and HotpotQA benchmarks.
Never have failed AI/ML workflow runtimes, never experience CUDA hell again. Diagnose ML runtime conflicts, estimate VRAM, and prevent expensive GPU training failures before you build.
Iroko AI deploys 5 specialized AI agents that monitor MTN Nigeria's enterprise documents 24/7, detect SLA breaches, compliance risks, and network anomalies in real-time — streaming every reasoning step live so operators see exactly how decisions are made.
AegisNexus AI is a real-time AI governance and prompt security platform that detects prompt injection attacks, analyzes threat levels, enforces safety policies, and visualizes adversarial simulations through an immersive cyber-defense dashboard.
GreenChain is a multi-agent AI system that audits supply chain carbon footprints in seconds. Upload shipping data and three AI agents extract shipments, calculate CO₂ emissions, identify hotspots, and generate a green sustainability roadmap.
SwarmAudit is a multi agent code audit dashboard that scans GitHub repositories for security, reliability, dependency, observability, performance, and production readiness risks.
An open-source agentic engine that drives Chrome through every available channel — DOM, accessibility tree, network interception, JS evaluation, multi-tab and multi-context. Each task graduates to a direct API call after first run. Linux + ROCm on AMD.
PatchPilot AI is a generic agentic code review copilot for C++, Java, JavaScript, Python, and C#. It analyzes simple and complex code, detects bugs, security issues, and performance bottlenecks, then generates fixes and test plans.
AgentMesh AI is a reliable AI task execution platform that transforms natural language into real-world actions using multi-provider LLM orchestration, async workers, watchdog-based reliability systems, and real-time execution infrastructure.
Al Agent Orchestrator for Real-Time Engineering Simulation. Powering the next generation of CAD/CAE workflows on AMD ROCm™ hardware.
A nanopayments demo showcasing autonomous agent-to-agent USDC transactions, real-time settlement feeds, and margin analysis for machine-to-machine commerce.
NeuralTrade v1.01 is an AI-powered trading agent that leverages deep learning and modular workflows to analyze markets, optimize strategies, and execute trades with adaptive intelligence for finance automation.