#gradio

An open-source tool to extract subtitles (.srt/.vtt) from Douyin video links via OpenAI-compatible ASR APIs. Supports batch processing and 1-click Docker deployment.

Multi-agent DevOps incident analysis - LangGraph orchestration, runbook RAG, Tavily research, vision intake, Slack/JIRA integration, Inspect AI evals. Eng Accelerator hackathon.

AI-powered text-to-3D model generation agent with MCP server support. Local models (Hunyuan3D, TripoSR, FLUX) + cloud APIs.

An AI-powered Fact-Checking Agent built with Python, Gradio, and Google GenAI.

Homeroom Copilot is an AI-powered educational decision-support tool that helps educators identify at-risk students, understand root causes, retrieve evidence-based interventions, and generate actionable support plans using small open-source AI models.

Medical RAG chatbot answering diabetic retinopathy questions with cited sources, built with LangChain, ChromaDB, sentence-transformers, and Llama 3.3 70B (Groq). Deployed on HuggingFace Spaces.

Agente de RR. HH. con LangGraph, RAG, FAISS, Groq y Llama 3.3 para responder consultas internas, solicitar información adicional y generar tickets de soporte.

台灣長照 2.0 資格初篩與補助試算 agent：模型只負責對話與意圖理解，金額與級別由版本化 Python 規則引擎計算，另有全文 PII 遮蔽、fail-closed 保守 intake 與 HITL 逐字鎖定發布。20 題固定診斷集下，3B 台灣地端模型端到端由 0/20 提升到 20/20、金額題 13/13、PII 洩漏 0 筆；586 項測試全過

Conversational AI assistant built with Python, Gradio and OpenRouter API.

An AI-powered multi-agent system for analyzing, validating, prioritizing, and managing municipal infrastructure reports.

Privacy-first local Ollama chat with expert personas, reasoning, multimodal input, context-aware history, and long-term conversation memory.

Evidence-grounded Agentic RAG platform for industrial root-cause investigation using Qwen3, BGE-M3, hybrid retrieval, LangGraph, verification, and human approval.

An open-source AI workflow platform for speech transcription, LLM-powered processing, and interactive transcript chat using any OpenAI-compatible API.

Easiest way to learn how to make a chatbot on Google Colab using the Large Language Model, Qwen.

An instruction-tuned conversational chatbot (Qwen2.5-0.5B-Instruct) with multi-turn memory, feedback-driven continuous learning, and a full MLOps pipeline (MLflow, FastAPI, GitHub Actions CI/CD) — DEPI Generative AI capstone project.

AI-powered Restaurant Chatbot built with Python, SQLite, LangChain, OpenAI and Gradio.

A CPU-friendly AI chatbot built with Python and Hugging Face Transformers — includes knowledge-base search, a Gradio web interface, guardrails, and persistent memory.

AI-powered Digital Twin built with Python, Gradio, and Groq LLM, showcasing my projects, technical skills, experience, and career journey through an interactive chatbot.

AI interview prep & performance analyzer — generates CV-grounded STAR interview guides via RAG, then scores practice video answers on content, speech, and visual delivery using Whisper, librosa & MediaPipe.

Hugging Face Spaces demos showcasing Crusoe AI managed inference — LLM game battles, model arenas, voice, and agent demos

Hands-on Python lab for ElevenAgents and ElevenAPI: Brazilian-market voice scenarios, latency checks and thin browser surfaces (Gradio + Next.js).