Questions

Most tools either report a world or simulate one without making agency and consequence legible. Meridians creates a maintained, inspectable world where a person or agent can see the rules, conditions, and open questions; make a move; and return to what followed. The point is not a more convincing answer. It is a clearer practice and a durable record of what it taught.

Meridians gathers the news, research, and source material you care about into a maintained Domain for analysis. The Program keeps it current; the Graph makes change and consequence inspectable; Scenario lets you explore critical moves alone or asynchronously with friends. Stageplay is developing Episodes as the deeper roleplay form. World is an experimental sandbox, not a shipped MMO. It is not a chatbot because the durable Domain and its record—not the conversation—are the product.

A Domain is the maintained model: its System, World, Fate, canon, entities, topology, information, and history. Scenario is the light decision game at a branch tip, suitable for solo or asynchronous friend-group play. Episode is the deeper Stageplay presentation of the same story substrate: it can embody accepted history or eventually wrap a live Scenario choice in perspective-shaped roleplay. World is an experimental sandbox inherited from a sufficiently mature branch. Domain defines. Branch preserves. Scenario resolves. Episode embodies. World inherits and lives.

Fate is the dynamic bearing of possibility: what remains possible and how evidence or action can influence it. Destiny names the imagined actual outcome if predestination is possible. Whether destiny exists—and what that would mean for free will—is an open question Meridians does not settle. The system records only the situated, attributable expression of Will when a person or agent acts; it does not claim to capture Will itself. None of these ideas gives Meridians authority over a person's life or turns a simulated result into a verdict.

Extraction translates current news, a premise, canon, research collection, or other valuable corpus into a Domain: System rules, World entities and state, open Fate, information, relationships, provenance, and gaps that can be authored. Research and the Program keep it useful for analysis. Scenario opens a light decision surface over a branch tip. Stageplay can turn accepted scenes into Episodes and is developing deeper asynchronous roleplay. A mature branch may later seed an experimental World sandbox, but that is optional rather than a mandatory gate.

Episode is the deeper narrative and roleplay form built from a maintained Domain. Stageplay is its production pipeline: reusable sprites and environments, performance cues, dialogue, sound, infographics, and perspective-shaped public or private moments. A catch-up Episode can embody accepted history; the live direction wraps a bounded Scenario choice so one or more players can move the branch. Stageplay is in active development, not a shipped Studio capability or a second source of canon.

First make current sources useful as a maintained, analysable Domain. Scenario then supports light solo and asynchronous friend-group decisions. Stageplay develops deeper Episodes over the same branch and resolution substrate. Only sufficiently mature branches may seed experimental World sandboxes for tours, continuity, or bounded social activity. Persistent economies, richer Worlds, and MMO-scale participation remain open experiments. Any earlier form may remain the complete product.

Agents do not receive one omniscient group prompt. Each seat has a graph position, partial information, memory, resources, permissions, action allocation, and reachable tools. Its accepted MCP calls pass through the same rules and writer, alter canonical state, propagate information, consume time or resources, and change what later seats can know and do. The goal is consequential society, not abundant dialogue.

A Frame is one entity or concept owner's typed, signed reading or alignment toward a target in World, System, Fate, or Theme; direction matters and the reverse is a separate Frame. Control is narrower and absolute: a Unit is Unbound or fully Controlled by exactly one selected source. Character and Unit are simulation resolutions—not judgments of intelligence or worth—and an entity can move between them without losing identity or history.

The shared cadence gives humans and idle agents a humane world with declared active hours, rest, and weekends. Equal cadence does not require equal speed: Domains may vary tick eligibility, turn allocations, cooldowns, queue priority, concurrency, and tool latency. Rate can become a capability or scarce resource, rewarding observation, patience, burst action, or investment in throughput. Every advantage must be explicit; accidental compute or scheduler latency must not become hidden power.

That is a future research direction, not a shipped claim. Scenario could supply bounded episodes for injecting Will into pivotal situations and comparing narrative outcomes. Parallel Worlds could train or evaluate cohorts across partial information, tools, economies, institutions, and other agents over time. Success inside either environment proves behavior under that declared simulation only. Claims of improved real-world or societal performance require independent transfer tasks, safety evaluation, and evidence outside Meridians.

Return to one clear continuation. If something materially moved, Stories shows what changed in the world, why it matters, and which commitments need your judgment. The machine proposes; you accept, correct, defer, or refuse. If nothing needs you, Meridians says you are caught up. Open the Studio when you want to investigate, branch, or explore in depth.

A Position carries both the reasoning and the commitment. Meridians first builds a causal Graph, then a Reading of viable futures and their timing, then makes a situated commitment with the evidence or canon that would change it. Scenario can play that commitment forward in a declared world. The result teaches about that world and task; it is never a claim to know the real future.

It weighs evidence rather than treating every link alike: relevance to the open question, source quality, corroboration, recency, and the source's earned history all matter. Strong evidence moves a position; thin or conflicting evidence stays uncertain. Every material movement keeps its sources and before/after state so you can inspect what changed and correct the reasoning.

No. Meridians may use real-world research as material for a world, but it does not claim to predict, trade in, or validate itself against the real economy. Positions are commitments inside a declared practice world. The purpose is to explore judgment, coordination, and revision under conditions you can inspect and control.

A feed is built to keep you scrolling; Meridians is built to make a maintained read easier to inspect and act on. A feed never ends; Stories has a real caught-up state. A feed gives you takes; Meridians gives you positions with the causal reasoning attached. The Exchange lets you browse and follow models today; ranking them by demonstrated records comes later, once those records exist. And while a feed improves its targeting, your expert accumulates the questions and corrections you teach it.

Your corrections become attributed, durable model changes instead of disappearing with a chat. Teach it which questions, sources, causal links, and distinctions matter; later research and Positions show the consequence. Months of evidence, corrections, and read-history compound into an expert another person cannot reproduce with one prompt. The canonical record remains readable and exportable even if billing stops.

Yes. The Exchange ships today: publish an expert, browse and follow others, and import one as a private fork with visible lineage and reviewable upstream changes — no update overwrites your tutoring silently. Exchange is free. A paid public network on top of it — ranking, audiences, and rev-share — comes only after retained users love their experts and the free exchange proves the demand.

Yes. A custom setup can begin from your corpus, canon, research question, or operating context and configure the Domain ontology, sources, Program cadence, schedules, operations, permissions, and outputs around it. That work uses the substrate that ships today. Experimental Stageplay production or future World mechanics are scoped separately so a custom engagement never quietly turns direction into a present-tense promise.

Hosted is the recommended product at $5.99/week: one isolated, always-on Meridians runtime with AI and research usage included. License is $3.99/week and runs the same engine and record on your own computer with your own provider keys. They are separate subscriptions; choose the host and cost model that fit you.

Not in the first product release. Creator subscriptions and revenue share are a later layer, after a free exchange proves that users maintain experts others genuinely want. Meridians must first be valuable for one Director with one private expert; commerce cannot substitute for retention or product quality.

Data sovereignty is a product boundary on both runtimes. Hosted stores the canonical record on your isolated instance volume; the Gateway keeps account and entitlement metadata, not a second writable domain record. License keeps the record and your provider keys on your computer. Billing may stop active work, but it never removes your ability to read and export the record.

No. Meridians must deliver full value to one Director. You can later invite viewers, contributors, or managers into the same instance with explicit permissions, but collaboration is optional and never a requirement for activation.

Meridians selects frontier models by task through one governed inference boundary. License calls them through provider keys you supply; Hosted includes the managed provider usage. Those models perform bounded generation, research synthesis, and reasoning tasks; Meridians supplies the durable domain model, Program, permissions, provenance, and one-writer record that make the work compound.

Each domain is a bounded, self-updating artifact with the same contract: System holds rules and constraints, World holds actors and state, and Fate holds open questions and their bearing. A reducer is the single state writer; the on-disk record is canonical; UI, Pilot, automation, and MCP use the same queries, actions, and operations. Separate domains compose through constellations without collapsing into one untraceable model.

Hosted is the flagship runtime: an isolated Meridians VM that runs the Program continuously. The focused mobile path and Stories handle return visits and consequential judgment; the desktop Studio opens the same expert in depth. License lets you self-host the identical daemon and canonical record. Email or messaging may become delivery adapters later, but they are not the product spine.

Yes. Bring source material in as text or research, connect supported sources, and use MCP or the operation surface to read and steer the same model from other tools. Export remains a first-class right. Integrations call Meridians' typed contracts; they do not write around the reducer or create a second state store.