Tryll

On-device AI for games and tools. Tryll runs small language models — and speech recognition, speech synthesis, and vector search — on the player's own machine. Instead of a single prompt call, you compose an agent: a workflow graph of typed nodes that retrieves from your own data, calls your game's functions, speaks and listens, and reads live game state. First-party clients for Unity 6, Unreal Engine 5, C++, and Python drive it over a binary protocol. No cloud API, no per-token cost, no network round-trip.

Start here

• Unity 6

  Drop a TryllAgentComponent on a GameObject and chat with it.

  First inference in Unity →

• Unreal Engine 5

  Drop a UTryllAgentComponent on an actor and chat with it.

  First inference in Unreal →

• Python

  Pip-install the client and see streaming tokens in 20 lines.

  First inference in Python →

• C++

  Clone, configure, build, and run a tiny chat demo.

  First inference in C++ →

What Tryll gives you

• A local model host. One server process, many clients. It loads a model once and shares it across every session that needs it, and it ships inside the Unity package and Unreal plugin — there is no separate server to install or point at. Model management →
• Agents are workflow graphs, not prompts. An agent is a typed graph of nodes — generate, retrieve, classify, branch, call a tool, speak — wired by named exits and passing values to each other through a per-turn slot blackboard. Workflows, graphs, and nodes →
• Your data, your rules. Ground answers in your own lore with on-device retrieval (dense, lexical, or hybrid), force machine-readable output with a GBNF grammar, and short-circuit off-topic or out-of-character input before a model ever runs.
• Voice both ways. Streaming text-to-speech with zero-shot voice cloning, and streaming speech-to-text with push-to-talk or hands-free turn taking — both on-device, alongside the language model.
• Live game state in, real actions out. Agent variables push the player's level, mood, or inventory straight into prompts and retrieval filters, and tool calling lets the model invoke your functions and answer from the results.
• Four first-party clients, and editor tooling. Thin, idiomatic wrappers over the same wire protocol — Unity · Unreal · C++ · Python — plus a visual graph editor, model manager, chat window, and turn inspector inside both engines.

Explore the docs

• Getting Started — tutorials for your first inference on each platform.
• How-to Guides — task recipes: RAG assistants, tool calls, streaming to UI, local model setup, guardrails.
• Concepts — the mental model: architecture, agents, workflows, RAG, projection.
• Reference — every field, every enum, every error code.

What you can build

• An NPC that talks in character — and keeps doing it over a long conversation, because history is projected and trimmed for you. Design an NPC prompt →
• An NPC that knows your world — quest logs, item descriptions, faction lore, indexed on-device and retrieved per line of dialogue. Create a simple RAG assistant →
• An NPC that acts — the model calls your functions (open the door, set the price, start the quest), you run them, and it answers from the real result. Define and handle tool calls →
• A conversation you can hold out loud — the player speaks, the character answers in a cloned voice, all locally. Add voice output → · Use voice input →
• Output your game code can trust — a grammar makes a reply parse-safe by construction, and game code can own the numbers while the model owns the wording. Constrain output with a grammar → · Keep merchant prices deterministic →
• A character that stays in its world — reject jailbreaks and out-of-character prompts with scripted replies, before spending a model call. Build an immersion guard →

Status and versioning

Tryll is in pre-release — expect breaking changes until the 1.0 API freeze. Every release documents what breaks and how to migrate; see the release notes.

Tryll is currently in closed beta: the source repository is private and stays that way, and builds go to partners we have an agreement with. To report a problem or ask a question, email support@tryllengine.com — please include your Tryll version, engine and version, and the relevant server log.