Memnest
Local-first memory for AI coding agents, via one MCP service
Unreal plugin wiring Claude, GPT and Gemini into UE5 (no GPU needed)
UnrealGenAISupport is the easiest Unreal bridge to try because it calls cloud APIs and needs no GPU. It wires Claude/GPT/Gemini into UE5 and ships an MCP server, with helpers for agentic NPCs and TTS. Community-built and MIT-licensed. 'Autonomous NPCs' is a toolkit to build on, not a finished feature. Verified on 2026-10-14.
Facts & pricing last checked October 2026. How we review
UnrealGenAISupport is an MIT-licensed UE5 plugin that wires Claude, GPT and Gemini into the engine, bundles an MCP server, and needs no local GPU.
UnrealGenAISupport is the Unreal bridge that is a thin API-integration layer rather than a heavy local tool. It connects UE5 to cloud LLMs (Claude Opus/Sonnet, GPT, Gemini, Grok and more) and ships an MCP server ("UnrealMCP") so an agent can act in the editor. Beyond editor automation it offers building blocks for agentic NPCs, text-to-speech, and 3D generation. It needs no GPU because inference happens in the cloud (an optional local Ollama path exists). It is a community project; "NPCs that run as agents" is a capability to build with, not a turnkey system.
MIT UE5 plugin wiring cloud LLMs + MCP into Unreal, no GPU.
Community open-source project (developer prajwalshettydev / MuddyTerrain). Not official.
LLM API integration (Claude, GPT, Gemini, Grok); UnrealMCP server; agentic NPC helpers; TTS; 3D-gen helpers; optional Ollama.
Unreal developers prototyping LLM-driven gameplay without local GPU.
Unreal developers and gameplay programmers.
Individual developers and small studios.
Unreal and GenAI communities.
A UE5 developer who wants cloud LLMs and MCP in-engine without GPU setup.
Not applicable — open source.
No — it calls cloud LLM APIs. An optional local Ollama path exists.
Claude, GPT, Gemini and others, plus an MCP server for editor automation.
The plugin is MIT-licensed; you pay only for the LLM APIs you choose to use.
Side-by-side pages for pricing, features, and best-fit use cases.
Local-first memory for AI coding agents, via one MCP service
Turn API specifications into docs, typed SDKs, and an MCP server
The big directory of MCP servers.
MCP server registry, in-browser inspector, and gateway with an LLM API bundled in.
Free, hands-on Toolglade courses that cover this kind of tool — start reading in a minute, no sign-up needed.