Technical challenges
These challenges are not an abstract promise. They come from the concrete fields of Où est Ava ? and Edugami, then GamiWays addresses them with reusable rules and measurements.
Reduce the perceived wait between an intention, a voice response and a video presence without promising fluidity that has not been measured.
The Core must observe delays at every step, choose graceful degradation when needed and preserve continuity of the experience instead of optimising a single isolated metric.
Resume a conversation without turning every session into an infinite, costly and unreadable history.
The question is not to remember everything. It is to distinguish what serves the current turn, what documents progress and what belongs durably to a relationship with a person.
Keep scenario rules, character role, available knowledge and conditions for moving between steps together.
The prototypes reveal narrative and learning choices that should not be left to one prompt. The Core must make them configurable, inspectable and testable.
Be able to integrate a commercial layer when it accelerates a field deployment without locking the experience, data or product decisions into it.
Interface contracts, observability and exit tests matter as much as choosing a provider. The Core stabilises these conventions so they are not reinvented for every project.
Diagrams & reference points
The diagrams are open to provide an overview. You can collapse them individually after reading.
This diagram follows a response from speech to avatar. It shows where time is spent and which points must be measured before optimising.
Hover a diagram arrow to see latency budget and each component's role.
Target timings · TTS+Avatar parallelization possible · LLM → TTS streaming
This diagram clarifies how experience roles, journey rules and services intervene during a session. It prepares the conventions the Core can reuse.
Target architecture
The Core does not aim to make Où est Ava ? and Edugami uniform. It stabilises the conventions that prevent rebuilding context, memory, rules and observation for every new experience.
Journeys, characters and production tools use clear contracts instead of logic specific to each screen.
The engine manages session state, progression rules, the available avatar and events to observe.
Context is assembled in bounded form so the experience remains coherent without becoming opaque or too slow.
Model, transport, persistence and observability services remain replaceable behind explicit operating conventions.
Core diagrams
These two reference points connect architecture layers and memories to what an experience must retain, observe and resume.
This diagram connects experience, orchestration, context and operations layers. It shows what the Core aims to stabilise across Où est Ava ?, Edugami and future experiences.
This diagram distinguishes turn, session and relationship memories. It helps decide what remains temporary, should be measured or becomes useful continuity for the person.
Up-to-date synthesis of GamiWays Core (shipped epics) and the Où est Ava ? prototype — against remaining R&D work.
Actual state of GamiWays Core (shipped epics) and the public Où est Ava ? prototype — vs. remaining R&D work.
GamiWays Core
Deterministic 7-dimension assembler — memory, scenario, RAG, GM directives, persona — with token budget and selection trace.
Context Engine v2 replaces ad hoc prompt assembly: seven dimensions (short-term memory, working memory, long-term facts, scenario config, RAG, GM directives, persona) merge under a strict token budget. Every trim is traced — essential for debugging avatar responses in production and comparing Où est Ava ? vs Core runs.
Où est Ava ? prototype
Remaining R&D
Tap an item to show its detail below.
Actual state of GamiWays Core (shipped epics) and the public Où est Ava ? prototype — vs. remaining R&D work.
GamiWays Core
Où est Ava ? prototype
Remaining R&D
Deterministic 7-dimension assembler — memory, scenario, RAG, GM directives, persona — with token budget and selection trace.
Context Engine v2 replaces ad hoc prompt assembly: seven dimensions (short-term memory, working memory, long-term facts, scenario config, RAG, GM directives, persona) merge under a strict token budget. Every trim is traced — essential for debugging avatar responses in production and comparing Où est Ava ? vs Core runs.
The GamiWays Core is a headless orchestration engine for guided interactive experiences. Explore the content → orchestration shift, then domains and principles — with links to portal details.
The shift
The Game Master drives the experience — the Core assembles context.
Durable session, 3-layer memory, typed RAG, GM directives injected each turn, unlockable avatars, measured progression. This is the GamiWays target — validated on Où est Ava ? (post-film) and Edugami (plastic clues).
Select a domain — prototype example, key principles and portal pages to go deeper.
Adaptive journeys with objectives and remembered progression.
The avatar guides learners through structured objectives: the GM unlocks steps, injects hints, adapts pace. Episodic memory avoids starting from scratch each session.
Concrete example
Edugami / Dilemme Plastique prototype — plastic clues, Race for Water.
Related principles
Tap an item to show its detail below.
Select a domain — prototype example, key principles and portal pages to go deeper.
Adaptive journeys with objectives and remembered progression.
The avatar guides learners through structured objectives: the GM unlocks steps, injects hints, adapts pace. Episodic memory avoids starting from scratch each session.
Concrete example
Edugami / Dilemme Plastique prototype — plastic clues, Race for Water.
Related principles
The Core is structured around precise concepts — each entry details the role, APIs, and what Où est Ava ? does with it in practice.
Shared Gamilab × Memoways vocabulary — from the Avatar + Game Master duo to runtime building blocks.
The two agents
Interaction surface — persona, own memory, voice and face. Does not decide the global narrative arc.
The avatar assembles a prompt from the Context Engine: editorial identity (7 fields in Où est Ava ?), user facts, visible RAG chunks, active GM directives. It responds in streaming; the GM works in parallel.
Où est Ava ?
In Où est Ava ?: Max, Où est Ava ? and other film characters — each RAG chunk is character_id-scoped to prevent persona leakage.
Experience model
Context & memory
Tap an item to show its detail below.
Shared Gamilab × Memoways vocabulary — from the Avatar + Game Master duo to runtime building blocks.
The two agents
Experience model
Context & memory
Interaction surface — persona, own memory, voice and face. Does not decide the global narrative arc.
The avatar assembles a prompt from the Context Engine: editorial identity (7 fields in Où est Ava ?), user facts, visible RAG chunks, active GM directives. It responds in streaming; the GM works in parallel.
Où est Ava ?
In Où est Ava ?: Max, Où est Ava ? and other film characters — each RAG chunk is character_id-scoped to prevent persona leakage.
Click a phase to explore goals and epics — data synced from the development repository.
Select a phase to explore goals and epics.
Phase B underway: extend the delivered Core with voice input/output, multimedia triggers, multiple scenarios, richer memory systems, and a user-facing frontend.
Current-phase milestones
Transition from the delivered Core baseline to the enriched-experience workstream, with voice, media and player experience priorities.
Scenario objectives tracking, progression state machine, GM-driven narrative milestones
STT pipeline (Deepgram / Whisper), TTS streaming (Cartesia / Inworld TTS-2), real-time audio delivery
GM-driven media events: image display, video playback, document reveal during conversation
Richer player experience beyond EPIC 7.1: session history, progression visualization, multi-device support, voice-ready UI
Analysis of identified gaps in the state of the art and their translation into product and business opportunities for Gamilab and Memoways.
Read by category
HeyGen · Tavus · Synthesia · D-ID
SadTalker · Wav2Lip · MuseTalk · Simli
VASA-1 · AvatarForcing · A²-LLM
Dec 2025 · $10.5M YC+Matrix · 20B DiT · 20 FPS
Memoways × Gamilab — R&D 2025–2028
Select a domain to compare gap, state of the art, and GamiWays opportunity.
Six structural gaps — and how Core + Où est Ava ?/Edugami prototypes address them.
Identified gap
No production-grade solution for 1h+ sessions without token explosion — partially addressed by Core v2/v3.
Best state of the art
Mem0 (-90% tokens, +26% accuracy) — not validated for multi-session avatars.
GamiWays opportunity
Delivered 3-layer architecture + avatar-specific SLM distillation — Où est Ava ? validates in real conditions.
Tap an item to show its detail below.
Six structural gaps — and how Core + Où est Ava ?/Edugami prototypes address them.
Identified gap
No production-grade solution for 1h+ sessions without token explosion — partially addressed by Core v2/v3.
Best state of the art
Mem0 (-90% tokens, +26% accuracy) — not validated for multi-session avatars.
GamiWays opportunity
Delivered 3-layer architecture + avatar-specific SLM distillation — Où est Ava ? validates in real conditions.
Rows reflect services currently documented in the STT, TTS and video avatar comparisons. A cell qualifies a documented service capability, not a promise of a complete pipeline. Click column headers to sort.
12 solutions shown
Agent vocal · Cloud
STT · Suisse
TTS · Cloud
TTS · Conversationnel
STT · Cloud
TTS · Cloud
TTS · Cloud / S1-mini
Target
Speech-to-speech · Cloud
Speech-to-speech · Cloud
TTS / agent · Cloud
STT · Open weights
12 solutions shown
Vidéo live · API
Vidéo live · EU
Vidéo live · API
Target
Vidéo live · API
Vidéo live · API
Vidéo live · GPU
Vidéo live · Open source
Vidéo live · API
Speech-to-video · API
Vidéo live · API
Vidéo live · Self-hosted