VedalAI/neuro-sdk

Neuro SDK + API for allowing Neuro to play games

What it solves

This project provides a standardized way for the AI personality Neuro-sama to interact with and play various video games. It solves the problem of bridging the gap between an AI's decision-making process and the game's input systems, allowing the AI to perceive the game state and execute actions within the game world.

How it works

The system uses a websocket protocol to communicate between the AI and the game. The AI receives a text-based description of the game state and sends back text-based actions. Because it relies on text descriptions, it is most effective for games with low actions-per-minute (APM) requirements, such as turn-based games or visual novels.

Who it’s for

Game developers and community members who want to integrate Neuro-sama's API into their games or create custom integrations for existing titles.

Highlights

  • Official SDKs for Unity and Godot.
  • Support for a wide range of games including Slay the Spire 2, Cyberpunk 2077, and Pokémon Platinum.
  • A comprehensive ecosystem of community-maintained SDKs for languages like Rust, Python, Java, and C++.
  • Testing tools like Randy (a random action bot) and Jippity (which uses OpenAI to mimic the AI's behavior).

Related

  • Project
    MaxBittker/rs-sdk

    A research-oriented framework for developing and testing autonomous agents within a simulated MMO environment, designed for studying goal-directed program synthesis and multi-agent systems.

  • Project
    zenstory-ai/novel-to-game

    NovelToGame is an open‑source set of AI‑agent skills that turn a full novel into a playable, source‑grounded game (web‑browser or 3D) with full design documentation and a single‑run QA. It works with Claude Code, Codex, or Kimi Code, requires no bundled engine, and records every mechanic’s citation to the original text.

  • Project
    Project-N-E-K-O/N.E.K.O

    N.E.K.O. is an open‑source AI companion that combines voice, text, and visual understanding with a five‑layer memory system and multiple avatar forms. It runs locally (Python 3.11) and can be deployed via one‑click binaries, Docker, or source build. Features include proactive chat, real‑time multimodal interaction, agent‑style tool execution, a plugin marketplace, and support for 14+ LLM providers. The project is Apache‑2.0 licensed and has active Discord/QQ/Steam communities.

  • Project
    a2aproject/a2a-js

    A TypeScript/JavaScript SDK that implements the Agent2Agent (A2A) protocol, enabling developers to build interoperable agent servers and clients that communicate via JSON-RPC, REST, or gRPC.

  • Project
    aartiq/servicenow-mcp

    An MCP server that connects AI clients like Claude and ChatGPT to ServiceNow, providing over 500 tools to query and automate the platform using plain English.