"How to configure Azure Speech" matching MCP servers:

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.

Self-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.

Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.

Zero-knowledge document vault backed by Azure Blob Storage with built-in MCP server. Client-side AES-256-GCM encryption, five tools (list, get, search, create, update), and OAuth-gated access for Claude.

Self-hosted knowledge backend for AI agents. Provides 11 MCP tools for hybrid vector + keyword search, container-isolated knowledge bases, and 4 storage connectors (S3, Azure Blob, MinIO, filesystem). Built with .NET, runs via Docker.

A codebase ontology and a cited wiki, both kept as Markdown in one folder on your disk. Typed graph answers — what a change affects, how two concepts connect, which wiki lines lack a citation — and every write lands as a Git diff a person reviews.

Provides OpenCode with adaptive long-term memory by storing preferences, lessons, and usage history locally in SQLite, enabling AI to remember and adapt to users through context-based learning.

Turn Obsidian notes into agent-ready context, preview-only plans, and safe repo handoffs.

Gives Claude persistent, local context about how you work, your weekly agenda, and shipped work, with automatic work logging and git integration—all stored privately on your machine.

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Persistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.

Portable, provider-agnostic memory for AI agents using Azure Data Explorer (Kusto) with temporal and semantic scoring.

Lets AI agents retrieve source-linked passages from a local folder of Markdown notes or an Obsidian vault, optionally following the explicit links between notes, and can also fetch passages from pinned public GitHub files you configure. It returns bounded evidence packets with original text, file paths and hashes so agents can answer from your material rather than generating content themselves.

Enables a small local LLM to build and maintain a project map by offloading event ID/date generation, batching, synchronization, recovery, and finalization to the server, so the model only decides what to read and how to classify.

Model Context Protocol (MCP) memory server built with Azure Functions and TypeScript, providing persistent knowledge graph storage for your preferred MCP client. Inspired by and forked from @modelcontextprotocol/server-memory

Serves portable behavioral identity models via MCP. Extracts how a person thinks, communicates, and makes decisions from text, then provides always-on identity context, semantic fact retrieval, keyword search, and provenance tracing through 4 tools and 1 resource.

A spaced repetition flashcard MCP server using the FSRS-5 algorithm that provides interactive card review, text-to-speech, and image support.

Local-first semantic memory server with project indexing for AI assistants. It enables AI assistants to store, retrieve, and search memories and project code using embeddings and vector search.

🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL. Features vector search, semantic knowledge storage, and efficient relationship management - perfect for AI agents and knowledge graph applications.

Combines bm25, vector and knowledge graphs to create a comprehensive memory solution. https://github.com/lumetra-io/engram-memory-mcp