"Trending MCP server for memory usage with GitHub Copilot integration" matching MCP servers:

Monitors your Cursor usage and provides a conserve flag to the agent, helping you manage request quota by batching questions, preferring defaults, and cutting unnecessary confirmations.

An AI copilot for marketing budgets that uses a 6-agent society with learned memory to manage ad accounts, built as a Model Context Protocol server for Qwen Cloud.

Enables agent-controlled Darkest Dungeon gameplay by providing game state, tactical context, validated semantic actions, and persistent campaign memory to AI assistants.

Slipstream - Built by Vektor Memory - a persistent multi-layered memory architecture. 4-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, DXT-MCP Cloak Tools.

An MCP-native agentic copilot for dental practices that orchestrates multiple MCP tools to analyze X-rays, pull patient history, generate drafts, and propose recalls, streaming results live to a React dashboard.

A meta MCP server that scales LLMs to 1000+ servers via automatic routing, without exposing all servers and tools directly.

Enables chat with multiple LLM providers (OpenAI and Anthropic) while maintaining persistent conversation memory. Provides extensible tool framework for various operations including echo functionality and conversation storage/retrieval.

Enables natural language control of quantum photonics experiments through the qudi framework. Supports safe instrument control, measurement execution, and safety system management with built-in runlevel protection and parameter validation.

Enables users to read compact game state, execute legal actions with freshness checks, and inspect action schemas and wiki details for the Steam version of Balatro through MCP tools.

Enables MCP-capable AI agents to generate and reorganize schematics, resolve LCSC components, place and route PCBs with custom DRC constraints, inspect design data, and safely apply, repair, or restore changes in native EasyEDA Pro and JLCEDA documents.

Implements a Model Control Protocol server integrated with Google Gemini LLM, providing a flexible framework for building AI-powered applications.

Hand a project over — to your next session, to Cursor/Codex/Gemini, to your successor — with the reasons attached. Local-first memory MCP for coding agents: decisions re-injected before the agent acts, drift detection across every project you run. One SQLite file, nothing leaves your machine.

Hosted memory for AI agents that learns from outcomes, with shared rooms. One key across Claude, Cursor & ChatGPT.

Smart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.

Persistent, structured memory server for AI agents using the Model Context Protocol, with categorized storage and tools to add, get, delete, and list memories.

A zero-dependency, file-based persistent memory system for AI agents with tiered memory, Ebbinghaus decay, and keyword retrieval.

Two-layer memory for AI agents. Episodes compress into identity. The only MCP memory server with an immune system. Patterns earn permanence through evidence, false knowledge gets caught and demoted, and stale information fades — so your agent's memory gets smarter over time, not just bigger. Zero dependencies. 5 tools. Works with any MCP client.

Memory for AI agents that can't hallucinate — answers only from stored facts with a citation, or honestly abstains. Provable forgetting (GDPR), valid-time, Merkle proofs, deterministic. MCP server, CPU-only, zero dependencies.

Exposes GitHub issue and pull-request triage capabilities to any MCP client: fetching repository context, classifying and prioritizing requests, finding duplicates, and applying labels, comments, assignments, closures, or reopenings. All writes are policy-gated, dry-run by default, and destructive actions require explicit two-step human confirmation.

Enables AI agents to persist memories across sessions and recall them through graph-traversal spreading activation over interconnected neurons with explicit relationship types, supporting multi-hop reasoning fully offline without embedding API costs.