#chromadb

職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost.

Open-source AI code reviewer that auto-reviews GitHub PRs LangGraph agents, knowledge graph blast-radius detection, mem0 persistent memory Zero cost, self-hostable.

Production RAG platform — multi-notebook document Q&A with Keycloak SSO, ChromaDB, Claude, Google Drive ingestion

Two-pipeline Agentic RAG system with side-by-side comparison. Custom sequential agent pipeline vs LlamaIndex inspired ReAct reasoning loop, with full chunk, trace, token and timing visibility for fine-tuning.

AI document assistant with a production RAG pipeline — hybrid BM25 + semantic search, cross-encoder reranking, and streaming answers. Built with FastAPI, Streamlit, ChromaDB, and DeepSeek LLM. Fully Dockerized and deployed on Railway.

AI Video Intelligence & Knowledge Synthesis Platform built with LangChain,LangSmith, ChromaDB, Whisper, and LLMs.

把任意抖音博主蒸馏成可对话的 AI 知识分身 · download → transcribe → categorize → RAG

AI Research Agent 2026 🔍 - Autonomous Deep Web Explorer & Adversarial Synthesis

AI-powered multi-agent research platform for literature discovery, synthesis, and citation generation using LangGraph, RAG, and Gemini AI.

🧠 A persistent memory RAG chatbot that never forgets. Uses Phi-3-mini LLM, ChromaDB vector database, and Ebbinghaus memory decay curves.

Memex.ai-Inspired AI Knowledge Base 2026 - Smart Markdown Wiki with Graph Search & Static Publishing

An automated customer support email handling system with a multi-agent LangGraph workflow that combines categorization, retrieval-augmented generation, and automated quality review.

Agente RAG conversacional sobre IA Generativa con Google Gemini, ChromaDB y LangGraph. Memoria por thread, interfaz Streamlit y base de conocimiento propia. Práctica final del Máster en Data Science e IA.

AI-powered research assistant that enables semantic search, question answering, and citation-grounded insights from academic papers using RAG.

🔬 Private AI research assistant like Google NotebookLM but 100% local. Upload PDFs, URLs & YouTube. Ask questions grounded in your sources. 12-provider AI fallback. Works offline.

RAG-based AI chatbot built with FastAPI, LangChain, ChromaDB, and LLMs, supporting document uploads, semantic search, context-aware conversations, and multi-format document question answering.

This a POC on Customer Support Agent built using RAG and LLM. The below course was used as reference to learn and implement the same: -https://www.udemy.com/course/build-a-customer-support-ai-agent-with-langchain/learn/lecture/56401085?start=1#reviews The course uses legacy LangChain version. The code repository uses Modern LangChain version.

RAG Chatbot built with FastAPI, Gemini API, ChromaDB, and PDF-based document retrieval.

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.

RAG data pipeline: FastAPI microservices, MinIO presigned uploads, Redis queue, LangChain + ChromaDB, Claude chat

A fully local RAG-based Q&A system - hybrid BM25 + dense retrieval, BGE reranker, Ollama LLM, FastAPI backend, and a clean web UI. No API keys needed.

AI-powered RAG chatbot that helps Indian farmers access government agricultural schemes using LangChain, ChromaDB, HuggingFace, and GPT

Ask a hotel PMS in plain English — a LangGraph Text2SQL agent with hybrid retrieval and full SQL transparency. Live demo + case study (source private).

Conversational AI agent over accounts-receivable data: a LangGraph ReAct agent with guarded text-to-SQL and RAG, full-stack (FastAPI + React), on synthetic data

AI-powered educational agent platform built with LangGraph, Agentic RAG, long-term memory, evaluation pipelines, and observability workflows for adaptive AI Engineering learning.

RAG Chatbot for a Real Estate Agency

A small, working Retrieval-Augmented Generation API (FastAPI + Chroma + Claude). Ingest documents, ask questions, get answers grounded only in your data with cited sources.

AI-powered FAQ chatbot with semantic search — understands meaning, not just keywords. Built with Streamlit, sentence-transformers, ChromaDB, and Groq LLM. Features a dynamic, hot-reloadable system prompt, two-sided chat UI, and guideline-driven handling of small talk, off-topic questions, and safety edge cases.

Production-style RAG operations console with grounded retrieval, document ingestion, evaluation, cost analysis, and bias-aware LLM judging.

🏥 AI-powered Clinical Document RAG Engine — Ask questions about medical documents, get precise answers with citations. 86% retrieval accuracy. Free LLM support (Gemini/Groq/Claude).

Federal Acquisition Regulation Retrieval-Augmented Generation (RAG) Chatbot

An AI Meeting Assistant that downloads audio/video streams, transcribes speech, extracts key decisions & action items using Google Gemini, and builds a local RAG vector store for interactive chat. Powered by a FastAPI backend and a Next.js frontend dashboard.

Production-grade multi-agent AI system with LangGraph supervisor pattern, RAG knowledge base (ChromaDB), and Anthropic Claude — routes queries between specialized triage, scheduling, and eligibility agents

Production-grade RAG PDF Chatbot built with FastAPI, LangChain, OpenAI GPT-4o, and ChromaDB.

AI-powered multi-agent business analyst that evaluates startup ideas through market research, competitor analysis, monetization, and risk assessment using LangChain.

🤖 ИИ-куратор для образовательной платформы

Local semantic memory MCP server for AI coding agents (Cursor, VS Code, OpenCode)

CampusMind is a dual-portal RAG chatbot web app for college campuses. Professors can upload PDFs like the academic calendar, syllabus, etc., on the professor portal, which are split and saved locally in ChromaDB. Students use a public interface to chat. The app pulls the exact text chunks from the database and uses Groq (Llama 3.3) to answer.

Tu segundo cerebro para proyectos e investigacion. Asistente de conocimiento local-first sobre n8n + RAG con citas exactas (Claude + Chroma + Next.js).

🧠 RepoMind — A RAG-powered chatbot that lets you ask natural-language questions about any GitHub repository, with answers grounded in the actual source code and cited by file & line number.