Vector Search

Persistent Cognitive Layer for AI Agents — MCP Server

Persistent memory for AI agents — store, retrieve and search knowledge across sessions

A Model Context Protocol (MCP) server exposing Gmail operations for AI agents

MCP server for searching Claude Code conversation history via Agent Genesis

Agent Brain MCP - Model Context Protocol server exposing Agent Brain as MCP tools, resources, and prompts

Integrate AegisDB as persistent memory for Claude Code (MCP server + hooks)

MCP server for Adminica — library search and RAG chat in Cursor, Claude Desktop, VS Code

MCP server exposing acatome-store tools

Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.

Branded server card for the Outlit remote MCP server that exposes customer context tools to compatible AI clients.

Search that learns from feedback, over text and images: embeds locally, sends DNA only vectors.

Recall over your markdown notes: vector search plus your [[wikilinks]] as a graph, in SQLite.

Deterministic evidence about embedding spaces and vector indexes: hubness, collapse, ANN recall

Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.

Split Markdown into chunks by heading. Each chunk keeps its heading path and line numbers.

Turn local text PDFs and HTML files into clean Markdown, tables kept. Runs on your computer.

Read, convert, search, diff and outline PDF, Word, PowerPoint, HTML and 40+ formats as Markdown.

MCP server for Zvec vector database

Claude Code MCP server for RAG and memory powered by zvec

AI-powered Zotero research assistant — a standalone MCP server with 36 tools for literature search, bilingual retrieval, reading analysis, citation management, and review writing.