"Ram" matching MCP servers:

Enables AI assistants to play Pokemon Fire Red through the mGBA emulator by providing tools for button inputs and screenshots. It allows for direct reading of real-time game state from RAM, including party information, player location, and battle status.

An MCP server that enables LLM agents to control a two-joint MuJoCo robot arm through tools for moving, reading state, and resetting. It deliberately omits inverse kinematics, so the agent must infer joint angles from observations.

Enables AI assistants to analyze documents larger than their context window by loading files into RAM and querying them via search, navigation, and Python execution tools. Supports recursive reasoning to process massive datasets in chunks using sub-agents.

Enables Claude and other MCP clients to play Pokémon games on emulated Game Boy/GBA or real Switch hardware by exposing tools for button input, reading RAM-decoded game state, screenshots, save states, and persistent markdown notes.

Monitors host CPU/RAM, local ports, and Docker containers, streaming live telemetry to a React dashboard over SSE. Exposes MCP tools to query system status, read environment logs, and execute remediation fixes via a local LLM agent.

A structured, persistent reasoning workspace for AI. 20 tools for thought chains, branching, revision, search, tagging, and SQLite session persistence that survives context window resets and server restarts.

MCP server that enables natural-language-driven, headless HEC-RAS modeling, letting agents inspect, edit, run, compare, and plot 1D/2D hydraulic models without the GUI.

Persistent project context (AGENTS.md), cross-session memory, and identity — discoverable by any MCP client.

Enables AI agents to inspect and free NVIDIA GPU VRAM by managing Ollama models, helping make room for loading new models.

Enables goal-driven mission orchestration for Goose, turning a user goal into a structured plan with an approval gate, isolated workers in git worktrees, dual validation, auto-correction, and crash recovery to produce validated code.

Facilitates two-stage reasoning processes using DeepSeek for detailed analysis and supports multiple response models such as Claude 3.5 Sonnet and OpenRouter, maintaining conversation context and enhancing AI-driven interactions.

A Node.js package providing Model Context Protocol server infrastructure for AWS Lambda functions with streaming response capabilities through Server-Sent Events.

Intelligent AI memory management system with ML auto-triggers that automatically saves and retrieves information across AI platforms without manual intervention.

Enables autonomous agents to perform CAD geometry calculations and retrieve Autodesk API knowledge via MCP, combining a native C++ geometry engine with RAG grounded on Fusion 360, APS/Forge, Revit, and Inventor.

An implementation of the Recursive Language Models architecture that enables AI agents to process massive documents by programmatically decomposing them into sub-queries. It allows for cost-effective and accurate reasoning across millions of tokens by treating long-form data as an external environment for root and worker models.

Open, secure runtime that puts Revit, Rhino, Navisworks, and Power BI behind one MCP call center, enabling an AI agent to orchestrate them directly instead of manually dumping data between disconnected apps.

An MCP server that brings a local MLX-powered decision layer to coding agents, letting them choose short workflow actions such as task routing, risk checks, next steps, and test/review decisions without cloud APIs.

Enables building production-grade RAG systems with agentic reasoning, hybrid retrieval, and MCP protocol integration for use with Claude Desktop.

Enables autonomous agents to discover and bid on unused LLM token quota through a machine-to-machine secondary exchange protocol. It utilizes a Proof-of-Residue handshake to verify compute capacity and facilitate the real-time acquisition of verified residue tokens.

Provides read-only knowledge search and guarded action proposal tools. Write-like actions require human approval and return traceable evidence with policy events.