"Exploring RAG through defined workspaces" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Bounded KVP, RAG search, and wipe receipts for agent jobs over remote MCP
XMemo is a user-owned Memory OS for AI agents, providing a shared, persistent memory layer across AI assistants, IDEs, CLIs, tools, projects, and sessions. It enables ChatGPT, Claude, Codex, Cursor, Gemini, and other supported AI clients to access authorized long-term context without requiring users to repeatedly explain their preferences, project decisions, or previous work. Beyond basic memory storage and retrieval, XMemo supports semantic search, contextual recall, memory updates and corrections, source attribution, version history, project-scoped context, task tracking, and governed memory lifecycle management. Identity-aware access controls, scoped authorization, and memory isolation help users manage which agents and workflows can access their information. XMemo also provides advanced capabilities for structured knowledge, reusable procedures, and memory consolidation through its broader Memory OS platform. Connect through hosted MCP with OAuth or bearer-token authentication, or integrate directly through REST APIs and supported client tools. Memory remains available across authorized clients and sessions, with user-controlled access, export, and deletion. Website: https://xmemo.dev Documentation: https://xmemo.dev/docs
Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
A personal RAG database you build from chat, so AI creates work that sounds like you.
Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website.
Evidence-backed follow-through memory for what you owe, await, and need to remember.
Human-authored personal context before AI guidance, built through private structured reflection.
Knowledge Base von designare.at – Michael Kanda, Web & KI aus Wien. Semantische Suche über RAG.
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
- Lexpad – Vocabulary Notebook & FlashcardsOAuth via extensionapp.lexpad
Lexpad is a vocabulary notebook and flashcard app with spaced repetition (Leitner boxes) for learning words in 81 languages, including English, Spanish, French, German, Arabic, Turkish and Persian. Connect it to ChatGPT, Claude or any MCP client, and your assistant works with the words you collected yourself: • Save words and phrases you ask for, with meanings, example sentences and a level (A1–C2). • Find anything: browse and filter your whole notebook by due, new, struggling, starred or mastered words, level, topic or date added. • Practise: get quizzed on today's due words. Every answer counts as real review, moves the word through the Leitner boxes and keeps your streak. • Edit: fix spellings, change or reorder meanings, star or retire words. Deleting needs its own permission, and the assistant asks first. Lexpad never invents vocabulary: it only works with the words you add, by hand, from a text, or imported from Anki or a Kindle. Sign-in is OAuth on a Lexpad page; your password is never shared, and you can disconnect at any time. Works alongside the Lexpad web app and Android app. Guide and example prompts: https://lexpad.app/features/assistants
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Search your knowledge bases from any AI assistant using hybrid RAG.
Save and retrieve your chosen context, manage shared workspaces, and track project time.
Persistent identity, memory, and mission tracking for AI agents. Gives any agent a named handle, cross-session memory, real-time activity reporting, and a secure API key vault — all through one MCP URL.
SPM turns project knowledge into scoped, temporal, verifiable and injectable context for AI agents. It structures and summarizes project memory, tracks original intent, working state, current truth and history, preserves source traceability, and creates context packs that agents can query, verify and consume through MCP, CLI or API. The hosted MCP surface is project-scoped and does not expose billing, checkout or destructive admin tools.
