Pedagogical mode + Narrative mode, shared engine.
Hover over engine components for technical details. Both modes share the same infrastructure.
No solution combines all 5 criteria.
Hover over cells for details. Full latency benchmarks in State of the Art.
| Solution | Real-time <2s | Behavioral fidelity | Sovereignty | Conv. memory | Narrative control |
|---|---|---|---|---|---|
HeyGen Commercial | ◐ | ✗ | ✗ | ✗ | ✗ |
Synthesia Commercial | ✗ | ✗ | ✗ | ✗ | ◐ |
NVIDIA ACE Enterprise | ✓ | ◐ | ✗ | ✗ | ✗ |
Beyond Presence Enterprise | ✓ | ✗ | ✗ | ✗ | ✗ |
HeyGem OS Open Source | ✗ | ✗ | ✓ | ✗ | ✗ |
GamiWays Target | ⚗ | ⚗ | ✓ | ⚗ | ✓ |
HeyGen · Synthesia · Flowise vs GamiWays
Comparison on 7 criteria. Full analysis of 11 solutions in State of the Art. R&D challenges detailed in Research Challenges.
Two prototypes validated with real users.
Le Dilemme Plastique
Educational tool on ocean plastic pollution. Students converse with an AI avatar 'Peter' who guides them through environmental science topics.
Parle à AVA!
Interactive narrative experience allowing viewers to converse with characters from Romed Wyder's dystopian film 'Where is AVA?'. Photorealistic avatars of film characters.
Operational today vs. R&D required.
Production pipeline, API + SDK, Swiss-hosted, optional HITL
Swiss GPU cloud for sovereign open-source AI deployment
Tested with real users, documented feedback
Content database with rich metadata
Multi-agent orchestration, RAG integration
Architecture for long-duration sessions without token explosion
Generation <500ms with body language and behavioral coherence
Capture of individual prosodic fingerprint
From content delivery to interactive experience orchestration.
The GamiWays Core is a headless orchestration engine for guided interactive experiences. It is not an application — it is a foundation layer reusable across multiple products: learning, storytelling, cultural mediation, corporate training.
Adaptive learning experiences — the avatar guides learners through structured objectives, remembers their progress and adapts content.
Interactive narratives where characters remember, evolve and respond to viewer choices — beyond linear dialogue.
Virtual guides for museums, heritage sites and exhibitions — context-rich, multilingual, sovereign experiences.
Professional situation simulations with specialized avatars — onboarding, compliance, soft skills, continuous assessment.
6 guiding principles
Technology serves the conversation — never the reverse. Every architectural choice is evaluated against the final user experience.
Decide before generating. The Game Master evaluates global context and guides the experience asynchronously — LLM generation is a consequence, not a starting point.
What we inject into the LLM defines what we receive. Context management (memory, world, knowledge) is the primary technical differentiator.
No provider lock-in. The Core can switch between OpenAI, Anthropic, Mistral or self-hosted models without changing business logic.
The Core does not include UI, voice, video avatars or authoring tools. These layers build on top — the Core stays minimal, focused, stable.
Latency, cost, tokens, quality — measured from day one. Evidence-based iteration, not intuition.
Avatar + Game Master: two agents, one experience.
The Core is structured around precise concepts that define a shared vocabulary between Gamilab and Memoways.
| Concept | Role | Description |
|---|---|---|
| Avatar | Conversational actor | AI persona with identity, personality, autonomy and its own memory. Interaction surface — not the product itself. |
| Game Master (GM) | Async director | Understands global experience state, guides asynchronously via triggers and directives. Decides when to intervene, switch avatars or inject guidance. |
| Session | Durable container | Container for a user run within a scenario. Persists across conversations, maintains global progression state. |
| Conversation | Dialogue episode | Bounded dialogue episode with one avatar within a session. Each conversation has its own sliding window context. |
| Scenario | Experience template | Defines objectives, assigned avatars, knowledge sources, progression rules and completion conditions. |
| Memory | 3-layer system | Working memory (sliding window + cumulative summary), episodic persistence (session summaries), long-term user facts. Deterministic selection policy. |
| Context Manager | Context assembler | Assembles 3 dimensions: Memory (what happened), Experience/World (rules, objectives), Knowledge (external sources). Deterministic injection into the LLM. |
| Knowledge Pipeline | Internal RAG | Ingestion (PDF, MD, text), chunking, embeddings, pgvector retrieval, context-aware filtering. Compaction and injection into the GM/Avatar flow. |
Three phases, one vision.
Build and validate the fundamental loop: user input → context assembly → orchestrated avatar response → memory update. Operational back-office. Text-based prototype with one real scenario.
Add voice (STT + TTS streaming), multimedia triggers, multiple scenarios, richer memory systems, and a user-facing frontend.
Prepare the platform for advanced integrations: expressive avatars, multi-tenancy, scaling, SDKs and partnerships.
Full epic table with ✅/🔄/⏳ status — synced from the development repository.