pgvector

Agentic RAG research paper reading assistant with PDF ingestion, pgvector retrieval, LangGraph workflow, streaming chat, evidence sources, and OpenAlex/web search integration.

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

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。

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

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

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。

🚀 Opendray v2 2026 – Universal AI Agent Gateway (Slack, Telegram, Discord, DingTalk)

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.

Self-healing RAG on n8n with LLM-as-judge eval, drift detection, investigator agent, and canary A/B deploys.

Self-hosted memory for Claude — markdown knowledge base with wikilink graph, hybrid semantic search (pgvector + Ollama), and a first-party MCP server. One docker compose up.

A full-stack equity research platform pairing retrieval-augmented filing analysis with a deterministic quantitative engine — cited document Q&A, DCF valuation, ratio diagnostics, peer benchmarking, sentiment, and portfolio analytics. Built with FastAPI, React, and PostgreSQL/pgvector.

Open-source enterprise AI agent platform for centrally governing agents, tools, memory, RAG, approvals, and durable workflows with FastAPI, LangGraph, LangChain, and LangSmith.

Human-in-the-loop equity research agent: SEC-filing RAG with cited evidence, deterministic risk guardrails, and live execution through Robinhood's Trading MCP

AI-помощник по документации: Go + Next.js + pgvector + Ollama

Full-access local harness for Codex-style agents, subagents, and connector orchestration

Enterprise-grade agentic RAG chatbot — Python 3.14 / FastAPI / LangGraph orchestration, PostgreSQL + pgvector hybrid (dense + BM25) retrieval with cross-encoder reranking, Keycloak OIDC auth, MinIO object storage, arq ingestion workers, DeepEval scoring, and a pixel-perfect React 19 + Vite + TypeScript UI.

RAG over a Twitter/X bookmark corpus: pgvector + Postgres full-text search hybrid retrieval on Neon, OpenAI embeddings, Claude generation, eval harness with recall@k and MRR

Chat with your documents — production-grade RAG on Spring Boot 4 + Spring AI 2.0 + pgvector, exposed as both a REST API and an MCP server for Claude Desktop, with eval-gated CI and LLM cost observability.

100% Air-Gapped Local Autonomous Agentic Financial System. Features double-entry SQL check constraints, Ollama LLMs, FastAPI pgvector semantic search, and R Plumber predictive forecasting. $0 token costs.

AI agent development platform built on Flowise 3.1.4. Visual drag-and-drop builder for AI agents, chatbots and RAG pipelines, with pgvector PostgreSQL and production Docker deployment.

Standalone AI personal-finance assistant: LangGraph agent with tools, RAG and a semantic cache (FastAPI + Postgres/pgvector + Anthropic).

RAG-based document Q&A API — Spring Boot, Spring AI, Anthropic Claude, pgvector

Masar AI — agentic RAG over Dubai RTA open data. A 14-agent LangGraph orchestration with a corrective loop, hybrid retrieval (pgvector + Postgres FTS), Text-to-SQL, and deterministic fare arithmetic. Bilingual AR/EN, fully cited, runs on free-tier/local inference. Independent academic project, not affiliated with RTA.

A-port — a decentralized-style Knowledge Marketplace for AI agents to publish, search & buy premium data and analytics (Next.js + Supabase + pgvector).

rag, n8n, fastapi, pymupdf, supabase, pgvector, eu-ai-act, regulatory-tech, claude-api, openai-embeddings

An enterprise-grade Retrieval-Augmented Generation (RAG) engine built with Spring Boot and Spring AI. It performs semantic search and LLM-augmented analysis across open-source codebases using PGVector and OpenAI embeddings.

Retrieval-augmented chatbot demo — chunking, embeddings, grounded/cited answers. Node.js, TypeScript, OpenAI API, pgvector.

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.

Agentic pipeline that classifies router logs, filters noise, detects anomalies, and generates engineer-readable diagnoses using LangGraph, Groq, and pgvector.