Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 38 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).

A zero-configuration RAG memory server for MCP clients

PostgreSQL-based RAG Memory MCP Server with Supabase - knowledge graph + semantic search

Local, privacy-first RAG memory system for Claude Code

Local RAG memory system for coding agents

Universal RAG Memory MCP Server for AI assistants

Benchmark adapters and execution for agent-runtime across coding, tool-use, RAG, memory, browser, and terminal tasks.

Genkit AI framework plugin for GoodMem, a retrieval-augmented generation (RAG) memory service.

DeepSeek Harness plugin: a graphical project orchestrator — Kanban board, SQLite task store, RAG memory (local embeddings), model routing (pro/flash/flash-vision-exp/local) with temperature presets, and a God-mode agent that plans and delegates to subagen

RAG + Context Management MCP server: long-term memory, vector storage, knowledge retrieval. Run with npx, zero external APIs.

Provider-neutral Stackline AI contracts, server core, RAG, memory, and adapter interfaces.

Universal AI memory core — architecture enforcement intelligence with real-time dashboard, RAG memory, and rule distribution

OpenClaw native plugin for PostgreSQL-backed RAG, memory, and persona management

Production-grade multi-agent harness for SDD-BDD-TDD software development. RAG memory (BM25), Obsidian vault, MCP server, agent auto-generation. Compatible with Claude, Codex, OpenCode, Kimi, Qwen, DeepSeek, and any AI tool.

The full-stack AI SDK for building intelligent, multi-channel AI agents with RAG, memory, tool calling, and provider fallback — built by Classgrid.

A zero-configuration RAG memory server for MCP clients

n8n community nodes for RAG Memory Service - conversation memory management with vector search

AI-Native SDLC Framework for Claude with 18 specialized agents (BA, Database, Backend, Frontend, QA, PM, AI/ML, MCP), 98%+ context retention via RAG memory, automatic quality gates (80%+ coverage, OWASP, WCAG 2.1 AA), and 12 production MCPs. Free & open s

MetaHarness example — Pinecone RAG memory agent scaffold with tiered routing, MCP default-deny, and verification gate (npx @metaharness/example-pinecone my-bot)

Framework-independent DevTools core for the AI Copilot SDK - projects the telemetry diagnostics stream into inspectable runs, messages, context, state, tools, security, RAG, memory, agents, workflows, events and traces; safe debug-bundle export/import; an