Definition and scope
The continuity library explains how meaningful gaming context can be captured, separated, corrected, and restored across time. It covers the emerging continuity-companion type, intentional save state, general memory, multiple games and runs, conversational restore points, and one disclosed implementation: Companion Play.
A dedicated cluster gives long-term player context the same analytical depth usually given to live coaching.
Why the distinction matters
The index organizes ordinary links so readers and crawlers can discover the full cluster without a scripted interface.
For browse continuity concepts, the decisive question is what information the system can use, what role it performs, how long the context remains relevant, and what the player can inspect or control.
How to apply the idea
Start with gaming continuity, then choose the page matching your memory, restore, scope, or implementation question.
Start with the smallest useful context. Name the relevant game, run, character, or interaction horizon; distinguish verified facts from player statements and model inference; then link the result to a visible source or restore point when it must remain durable.
- Identify the primary player need.
- Choose the companion type or comparison level.
- Define inputs, authority, retention, and deletion.
- Test the likely failure mode, not only the ideal response.
Boundaries and caveats
The library does not claim that continuity companion is already a universal market term.
Product labels are not enough evidence. Current features, privacy behavior, platform access, and compatibility should be checked in official documentation. A fluent response can still contain an incorrect fact, stale state, or a plausible merge of two different runs.
A practical evaluation model
Evaluate a companion across five dimensions: context input, system role, action authority, time horizon, and player control. Add source quality and privacy when the system uses external knowledge or stores durable state.
This model keeps interface features in perspective. Voice, screen capture, an avatar, and a dedicated app can improve a particular implementation, but none of them defines the entire AI gaming companion category.
Browse the library
Continuity
- What Is Gaming Continuity?Gaming continuity is the preservation of meaningful player context so the correct gaming thread can be resumed later. That context may include a game, run, character, location, decisions, objectives, relationships, questions, and narrative state. Continuity is about recovering relevance, not recording everything.
- What Is a Gaming Restore Point?A gaming restore point is a named or otherwise addressable record of meaningful game-related state. It gives a later conversation enough context to recover the correct game, run, character, decisions, progress, and open questions without forcing the player to reconstruct the entire journey.
- What Is a Conversational Save State?A conversational save state is a structured, intentional record of context created inside or for a conversation. In gaming, it can preserve the player’s current run, character, decisions, progress, goals, questions, and narrative situation so those details can be restored in a later chat.
- How Does Cross-Chat Gaming Memory Work?Cross-chat gaming memory makes game-related context available outside the conversation in which it was first expressed. It may rely on general platform memory, an application record, or an explicit save state. Reliable gaming continuity needs identity, scope, provenance, and a way to correct stale information.
- What Is Cross-Game Gaming Continuity?Cross-game gaming continuity is a model that preserves context for more than one game while keeping each game, run, character, and goal distinct. It supports gaming as a continuing part of life rather than treating every title as an isolated app session.
- How Should AI Separate Multiple Games and Runs?An AI companion should separate multiple games and runs with explicit identifiers and scopes. A useful hierarchy is player, game, run or campaign, character or party, restore point, and timestamp. The system should ask before merging records that could refer to different playthroughs.
- General AI Memory vs Game Save StateGeneral AI memory usually keeps useful context for personalization and future conversations. A game save state is intentionally captured, scoped, and addressable. Memory may recall that someone enjoys an RPG; save state should restore the correct character, run, decisions, progress, and unresolved goals.
- What Is a Continuity Companion?A continuity companion is an AI system that preserves meaningful gaming context and restores the correct thread across sessions, chats, games, devices, characters, or separate runs. Its defining action is not watching the current moment; it is helping the player return to a meaningful journey later.
- What Is Companion Play?Companion Play is a continuity-companion implementation created by Raynor Eissens. It treats saving meaningful gaming state as an action within an existing LLM conversation, creating an addressable restore point for a later conversation. It is one implementation of the wider continuity-companion concept.
- Intentional Memory vs Associative MemoryIntentional memory is created or confirmed for a specific future purpose. Associative memory is recalled because a system judges it relevant to the current context. Gaming continuity benefits from both, but changing run-specific state needs explicit scope and addressability to avoid collisions.
- Why Save Slots Still Matter in the LLM EraSave slots still matter because language models can hold or retrieve several plausible versions of a player’s gaming context. A visible slot distinguishes games, runs, characters, campaigns, and moments. It gives the player a stable handle for selecting the intended state instead of relying on similarity alone.
Frequently asked questions
What is the shortest explanation of “Gaming Continuity Library”?
The continuity library explains how meaningful gaming context can be captured, separated, corrected, and restored across time. It covers the emerging continuity-companion type, intentional save state, general memory, multiple games and runs, conversational restore points, and one disclosed implementation: Companion Play.
Does this require real-time screen access?
Not necessarily. Screen access is an input used by some coaching systems, not a requirement for the wider category.
What should a player or product team verify?
Verify the system’s actual inputs, action authority, source quality, privacy controls, retention, correction path, deletion behavior, and whether its visible product claims match its implementation.
Further reading
AI Gaming Companion Article Archive
The article archive collects every public editorial route by topic. Use the cluster indexes for focused reading or the HTML sitemap for a complete route list. Machine-readable article metadata is available from the public data endpoint and RSS feeds.
Definitions and Category Foundations
The definitions cluster establishes what an AI gaming companion is, the five primary types, how the category developed, and which terms should remain distinct. Start here when a product label or search query uses companion, assistant, coach, NPC, agent, or memory ambiguously.
The Five AI Gaming Companion Types
The type library classifies AI gaming companions by primary role: coaching advises, in-game inhabits, agentic acts, social relates, and continuity preserves. Each type page explains defining traits, examples, exclusions, design questions, and links to relevant comparisons and use cases.
AI Gaming Companion Comparison Library
The comparison library distinguishes concepts that are often collapsed by product copy or search queries. Each page states the shared ground, the decisive difference, a compact evaluation model, and the limits of the comparison. The goal is architectural clarity rather than declaring a universal winner.
Research and Concept Essays
The research and concept archive examines interface models that sit behind companion products: session boundaries, save points, public performance, private continuity, player journeys, ambient hardware, relationship framing, and specialized state. These are reasoned editorial essays, not claims of settled academic consensus.