PostgreSQL

코스닥 DART 공시 실시간 분석 + 섹터 공포·탐욕 지수 + 사주 기반 종목 궁합 + 페르소나 투자 AI. Supabase·Neon·Redis·Vercel $0/월 인프라. Google 로그인으로 무료 이용.

Multi-agent AI runtime with OS-inspired primitives — job scheduling, DAG orchestration, memory, tool execution and real-time observability. Built with FastAPI, Celery, PostgreSQL and LiteLLM.

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

End-to-end ETL pipeline using Apache Airflow that extracts data from CSV and REST API, transforms and validates it, and loads it into PostgreSQL with incremental loading and monitoring.

PostgreSQL + pgvector 本地知识库，支持 MCP 跨平台调用。OpenClaw/LiteLLM 文档，混合搜索，多 AI 共用。

Claude Code skills for keeping Visual Basic 6 codebases alive — conventions, CSEH error handling, late-binding ADO, and manual stack tracing.

Practical full-stack engineering roadmap with runnable HTML/CSS, React, TypeScript, Next.js, Node, Python/FastAPI, Java/Spring Boot, PostgreSQL, SaaS, RAG and AI agent projects.

Trustworthy AI Knowledge Workbench — Verifiable RAG with citation tracking, document-grounded review, and self-contained desktop mode. Windows / macOS / Linux / Android / iOS.

Self-hostable AI bookkeeper for freelancers and small teams

Local-first MCP server for shared memory, reservations, handoffs, and review evidence across AI coding agents.

HermesClaw Zero‑Config Sidecar is a lightweight local vector‑memory engine for Hermes and OpenClaw. It runs as a zero‑config sidecar, providing fast embeddings, persistent memory, and instant retrieval for agents and MCP tools. Built for speed, simplicity, and full local control.

AI-powered knowledge management platform with RAG, multi-engine OCR parsing, vector search, wiki graphs, and Agent skill integration. Docker Compose deployment.

Persistent memory for coding agents over MCP — typed knowledge, semantic search, session lifecycle. PostgreSQL + pgvector, FastMCP.

Self-hosted, encrypted, provider-independent memory gateway for AI/LLM products — OpenAI-compatible, multi-tenant, auditable.

Scenery — one CLI tool for building, running, inspecting, and debugging Go backends. Local-first runtime, APIs, logs, traces, DB tools, generated clients, and AI agent skills included.

AI-powered automated job aggregation platform that scrapes, filters, ranks, and delivers fresher jobs, internships, and research opportunities through scheduled email alerts.

Fullstack AI Study Assistant with Spring Boot, React PWA, PostgreSQL, Cloudinary, and OpenAI vision grading.

A Rust-based PostgreSQL extension that makes relational query optimizers natively aware of LLM token costs, semantic entropy, and latency budgets.

Agent + Multimodal RAG 全栈学习项目：LangGraph PAE/ReAct、Multi-Query、BM25 + pgvector 混合检索、RAG-Fusion/RRF、MinerU/OCR/ASR、evidence 引用与 HITL；React + Spring Boot + FastAPI。

Agent-facing CLI harness for testing distributed systems

Vitalis.Med is an AI-powered Hospital Management System built with Next.js, NestJS, PostgreSQL, Prisma, Redis, and OpenAI. It streamlines patient care, EHR/EMR, appointments, billing, pharmacy, laboratory, telemedicine, and hospital operations with intelligent automation, real-time collaboration, and enterprise-grade architecture.

AI-powered project management SaaS — Next.js 16, TypeScript, PostgreSQL, Prisma 7, OpenAI, Stripe. Kanban boards, drag-and-drop, team collaboration, billing, CI/CD.

Sentinel is an AI-powered cyber threat intelligence platform for SOC analysts. It provides real-time threat monitoring, AI-based SQL injection and XSS detection, and security analytics. Built with a React/TypeScript frontend and a FastAPI/PostgreSQL backend, it offers secure, centralized cyber threat management.

An enterprise-grade, hybrid Retrieval-Augmented Generation (RAG) platform powered by LangGraph, Google Vertex AI (gemini-2.5-flash, text-embedding-004), PostgreSQL (pgvector), and Neo4j 5.20.

AI-powered campus placement exam simulator — Numerical, Verbal, Reasoning & Coding sections with live code execution and AI feedback

Autonomous software engineering platform. Submit an engineering job, watch a sandboxed AI agent plan, implement, test, review, and open a pull request.

Memory integrity for AI agents — Information-flow control against OWASP ASI06 memory & context poisoning.

Self-hosted real-time EN↔PT conference captions for Chrome, Deepgram, OpenAI-compatible APIs, and OBS