MaxBittker/rs-sdk

Runescape automation library, optimized for use by coding agents.

What it solves

This project provides a controlled, research-oriented environment for developing and testing autonomous agents. By using a game engine as a sandbox, it allows researchers to study goal-directed program synthesis, agent collaboration, and competitive behavior without the risks or constraints of real-world environments.

How it works

The project consists of a TypeScript SDK, a game server emulator (based on the LostCity engine), and a gateway that bridges the SDK with game clients. Agents interact with the game world through the SDK, which provides high-level methods for game actions. The system supports both interactive development via MCP (Model Context Protocol) and autonomous operation through standalone scripts that drive headless game clients.

Who it’s for

It is designed for AI researchers and developers interested in agentic workflows, reinforcement learning, or program synthesis who need a stable, repeatable environment to benchmark how different LLMs perform at complex, multi-step tasks.

Highlights

  • Research-Ready Sandbox: Includes accelerated XP curves and disabled anti-botting mechanics to focus on agent logic rather than game survival.
  • Multi-Agent Support: Facilitates research into agent-to-agent interaction, competition, and economic behavior.
  • Flexible Execution: Supports both interactive development via Claude Code/MCP and headless, large-scale bot fleet operations.
  • Benchmarking: Provides a structured environment to compare different LLM models on their ability to complete complex, goal-oriented tasks.

Related

  • Project
    TanStack/ai

    TanStack AI is a TypeScript‑first, provider‑agnostic SDK that lets you build streaming chat, tool‑calling agents, structured‑output flows, multimodal generation (image, audio, video), realtime voice, and sandboxed code‑execution agents. It offers composable activities, type‑safe contracts (via Zod/Valibot/JSON Schema), adapters for many LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.), and framework‑native hooks for React, Vue, Solid, Svelte, and Preact. Tree‑shakable and observable, it’s aimed at developers who want a unified, type‑safe way to integrate generative AI into web and server apps.

  • Project
    vercel/chat

    Chat SDK is a TypeScript library that lets you write a single bot and run it on many chat platforms (Slack, Teams, Discord, etc.) via plug‑in adapters, with built‑in support for AI streaming, rich UI cards, and state management.

  • Project
    photon-hq/spectrum-ts

    Spectrum‑ts is a TypeScript SDK for building AI agents that operate over real‑world messaging channels (iMessage, SMS, email, Slack, Telegram, etc.). It provides a unified, async‑iterator API, built‑in providers for major platforms, optional hosted infrastructure, and graceful startup cancellation. Install with `bun add spectrum-ts`, supply a Photon project ID/secret, and write a simple loop that replies to incoming messages.

  • Project
    codeany-ai/open-agent-sdk-typescript

    An open-source TypeScript SDK for running autonomous AI agents in-process, featuring a vast library of built-in tools and support for multiple LLM providers.

  • Project
    Rheosoph/flow-like

    Flow‑Like is a self‑hostable low‑code platform that lets developers build internal tools, data pipelines, document processors, AI agents and equipment automation using visual workflows (Flows) backed by a Rust execution engine. With >1,900 built‑in typed nodes, a package system for custom Rust/WASM nodes and UI widgets, desktop (Tauri) and web clients, and Docker‑Compose/Kubernetes self‑hosting, it offers a full stack for turning existing systems into reusable, API‑driven applications. Licensed under BSL 1.1, it targets technical teams that need on‑premise control over data and AI model execution.