# Limina > Limina is an agent-native real-time 3D engine: a single native binary (Rust host + V8 via deno_core + WebGPU via deno_webgpu + Three.js + native Rapier physics + bitECS) where LLM agents are first-class. External builders construct scenes over MCP; autonomous players perceive, decide, and act in-world. Every action is typed, permission-checked, and traced. Key facts for agents: - The engine is the substrate, not the brain: it owns the world, perception, the skill/MCP surface, and a durable event log. Decision-making and memory are pluggable and external. - Agents act only through 45 typed, versioned, permission-checked skills, exposed as MCP tools over in-process, stdio (`--mcp-stdio`), or websocket (`--mcp-ws`) transports. - Every action emits a typed, sha256-chained event into a durable, replayable world log. ## Documentation - [Introduction](https://www.liminaengine.com/introduction): Limina is an agent-native real-time 3D engine: one native binary where LLM agents build and inhabit a high-performance world. - [Getting started](https://www.liminaengine.com/getting-started): Prerequisites, building the single Limina binary, and running your first demo windowed and headless. - [Demos](https://www.liminaengine.com/demos): Every Limina demo: what each one shows, the capabilities it exercises, and the exact command to run it. - [Architecture & stack](https://www.liminaengine.com/architecture): The full Limina stack, layer by layer: Rust host, V8, WebGPU, bitECS, native Rapier/rayon/audio, and the crates that implement them. - [ECS & the world](https://www.liminaengine.com/concepts/ecs-and-world): How Limina stores the world: bitECS, SoA TypedArrays, opaque ent_ ids that are never reused, and native rayon ECS ops. - [The fixed-timestep loop](https://www.liminaengine.com/concepts/loop): Limina's fixed-timestep accumulator at 60 steps/s, render interpolation, determinism and replay, and why agent decisions resolve off the loop. - [Perception](https://www.liminaengine.com/concepts/perception): What a Limina agent perceives: a typed view of nearby entities, transforms, and recent events, built by a native batched CSR spatial query. - [Observability & the world log](https://www.liminaengine.com/concepts/observability): Limina's EventLoom-shaped event envelope, the sha256 continuous integrity chain, JSONL export, and the durable world log with replay and snapshot recovery. - [Skill / Hook Registry](https://www.liminaengine.com/pillars/skill-registry): The typed, versioned, permissioned path every agent action flows through. - [MCP Interface](https://www.liminaengine.com/pillars/mcp-interface): The discoverable, typed tool-calling contract — in-process, stdio, and WebSocket. - [Observability](https://www.liminaengine.com/pillars/observability): The typed event bus, causal trace trees, the sha256 chain, and JSONL export. - [Agent Ecosystem](https://www.liminaengine.com/pillars/agent-ecosystem): AgentComponent, the perception/decision/action systems, and the scheduler that runs them at scale. - [Skills reference](https://www.liminaengine.com/skills): Every built-in Limina skill — the agent-facing SDK surface — grouped by domain. - [Building with Agent Builders](https://www.liminaengine.com/building-agents/builders): Connect an external LLM agent over MCP and construct a scene, fully typed and traced. - [Building Agent Players](https://www.liminaengine.com/building-agents/players): Spawn an in-world autonomous agent that perceives, decides, and acts on the fixed loop. - [LLM Providers](https://www.liminaengine.com/building-agents/llm-providers): One async provider seam — scripted, local Ollama, or a cloud gateway — behind the agent loop. - [Roadmap & status](https://www.liminaengine.com/roadmap): Where Limina is: six phases shipped, the standing principles, and the numbers. ## For agents - [skills.json](https://www.liminaengine.com/agents/skills.json): machine-readable catalog of all skills (names, permissions, JSON-Schema inputs) - [llms-full.txt](https://www.liminaengine.com/llms-full.txt): the full documentation as a single plain-text file - [Agents hub](https://www.liminaengine.com/agents): machine endpoints and the MCP connect quickstart