What's New

Recent product updates

See what’s new in emergentic.ai, including new workflows, clearer tools, and fixes across the parts of the product you use most.

Latest Release Version 1.11.0

Larger 3D simulations, schedule controls, and model settings

Large live simulations run more smoothly, scheduled rooms are easier to block out and follow, and model settings are clearer for worlds and agents.

LatestJune 2, 2026

New

Schedule editors now support blocked time intervals, making it easier to mark breaks, off-hours, and other unavailable periods.

World settings now include shared agent model and service-tier defaults.

Agent settings now include clearer model labels, Auto model selection, and service-tier controls.

Improved

Large 3D simulations load and run more smoothly, with better movement updates and portrait rendering when a cast is too large for full 3D character models.

Schedule calendars now show blocked and skipped time more clearly while keeping dense room schedules easier to scan.

Duplicated projects now preserve more schedule, cast, action, location, narrative, and model settings.

Fixed

Scheduled simulations now communicate paused/waiting states more clearly while the scheduler is waiting.

Local media thumbnails load faster across project and agent surfaces.

Public API reads for larger worlds, active simulations, and latest logs are more consistent for client apps.

Recent Releases

Archive

A running feed of user-facing product updates.

Larger 3D simulations, schedule controls, and model settings

Latest

Large live simulations run more smoothly, scheduled rooms are easier to block out and follow, and model settings are clearer for worlds and agents.

Version 1.11.0

June 2, 2026

New

  • Schedule editors now support blocked time intervals, making it easier to mark breaks, off-hours, and other unavailable periods.
  • World settings now include shared agent model and service-tier defaults.
  • Agent settings now include clearer model labels, Auto model selection, and service-tier controls.

Improved

  • Large 3D simulations load and run more smoothly, with better movement updates and portrait rendering when a cast is too large for full 3D character models.
  • Schedule calendars now show blocked and skipped time more clearly while keeping dense room schedules easier to scan.
  • Duplicated projects now preserve more schedule, cast, action, location, narrative, and model settings.

Fixed

  • Scheduled simulations now communicate paused/waiting states more clearly while the scheduler is waiting.
  • Local media thumbnails load faster across project and agent surfaces.
  • Public API reads for larger worlds, active simulations, and latest logs are more consistent for client apps.

Public API docs, agent questions, and smarter recommendations

The public API is easier to build with, agents can be queried through grounded question jobs, and similar-agent recommendations can now be generated from simulation history.

Version 1.10.0

May 19, 2026

New

  • A new API Docs section now gives developers endpoint references, realtime event details, and copyable curl, Python, and TypeScript examples.
  • Agent question jobs can answer pair, location, and time-window questions using world, simulation, and log context.
  • Similar-agent recommendations can now be generated and fetched for a world or simulation, with filters for a specific agent.

Improved

  • Question and recommendation API calls can use agent names where supported, so callers do not always need to look up agent ids first.
  • API key settings now separate provider keys from service keys and show stored-key status more clearly.
  • API documentation and settings navigation now make it easier to move between endpoint references, examples, and key management.

Fixed

  • Public API responses now focus on the documented fields developers need for client apps.
  • Simulation log and agent list calls now use clearer pagination limits.
  • Question answers handle unsupported requests more consistently.

Shared simulations, scheduled rooms, and richer research tools

Simulations can now support joinable participant experiences, room schedules are easier to author and follow, and agents have stronger tools for working from video and media references.

Version 1.9.0

May 14, 2026

New

  • Shared simulations can now be opened with join links, letting guests bring one of their own agents into a host run through a scoped participant view.
  • Schedule-based plots now include room calendars, timezone-aware event editing, a simulation clock, and timeline views for following what is happening now and next.
  • New YouTube research actions can transcribe videos, sample frames or clips, and describe visual style so agents can work from pasted video links.

Improved

  • The simulation launcher now surfaces participant counts, join-link controls, and joined external simulations more clearly when starting or resuming a run.
  • Agent profiles now include public visibility controls for display name, avatar, backstory, and selected dynamic properties before they enter a shared simulation.
  • Media generation options now include more video and image-to-video workflows, with long-running media jobs handled more consistently in the background.

Fixed

  • Busy room simulations handle waiting, player interruptions, and multiple ready agents more reliably during live runs.
  • Shared chats and simulation views now preserve generated media context more consistently when logs are reopened or shared.
  • Narrative and storyboard tools are more accurate when placing panels in plot events and attaching shot media assets.

Workflow starters, richer topic networks, and faster agent setup

Starting a project now includes guided workflow presets, simulation setup points more directly toward first useful runs, and topic graphs and batch agent tools are more robust.

Version 1.8.0

April 22, 2026

New

  • New project workflow starters can prefill behavior sandbox, narrative/story design, virtual event twin, and game design worlds with useful starting context.
  • Topic analysis now separates stable and emerging topics, adds semantic topic links, and surfaces agent communities based on shared topic membership.
  • Actions can now be assigned to many agents from one modal, and new worlds get a default movement action with location-aware schema setup.

Improved

  • The simulation launcher now gives clearer next steps for defining the world, creating a cast, and running the first scenario.
  • Batch agent creation now uses Gemini 3 Flash for generated agents.
  • The homepage and project creation copy now better reflect games, stories, virtual events, and persistent agent worlds.

Fixed

  • Batch agent generation is more tolerant of duplicate names, already-existing names, and model responses that include trailing content after valid JSON.
  • Topic graph layouts scale better for larger semantic networks, with clearer labels, agent overlays, and topic inspector metadata.
  • Admins can now reset a user's billing tier override and see the fallback plan that will apply afterward.

Graph views, batch agent creation, and a faster playground path

Live simulations now have richer 2D graph views alongside 3D, large casts are faster to create from one concept, and the path into the playground and recent projects is clearer.

Version 1.7.0

April 16, 2026

New

  • Live simulations now include Agent and Meaning graph views, so you can switch between 3D, social structure, and topic-level conversation views while a run is active.
  • The simulation canvas now supports fullscreen viewing with clearer controls, current speaker cues, activity badges, and clickable details for agents, communities, and topics.
  • Agent creation now includes a Batch mode for generating a cast from one concept, assigning shared actions, and choosing selected or random starting locations.

Improved

  • Project browsing now separates recent projects from older projects, making larger workspaces easier to scan without losing access to the full list.
  • The marketing and pricing flow now points more directly to the playground, with simpler language for teams starting from a free workspace.
  • Cast and participant lists now show live badges when agents are in a running simulation, responding, or using an action.

Fixed

  • Stopping a simulation now resolves to a clearer stopped state instead of leaving paused or detached states visible in the UI.
  • Participant changes, scheduler waiting messages, and typing state now update more consistently while a simulation is running.
  • Simulation logs, generated media links, and game-agent state updates now stay in sync more reliably during active runs.

Unified simulations, clearer resume controls, and narrative polish

Simulation starts and resumes now center on one shared browser run, chat and 3D stay tied to the same live simulation more reliably, and narrative shotlists and media tools are easier to work through.

Version 1.6.0

April 12, 2026

New

  • The Simulation Launcher now uses one browser simulation path with clearer Start and Resume choices, running-run filters, richer run cards, and selected-run stop controls.
  • Simulation IDs are now easier to see and copy from chat and resume flows, making it simpler to reopen a run or hand it off to an external runtime.
  • Project deletion now includes a focused dependency preview for the cast, spaces, actions, plots, and simulation history that will be removed.

Improved

  • Chat and 3D views attach to the same live simulation more consistently, so leaving a view no longer implies that the run has stopped.
  • Agents handle player turns more cleanly, waiting for input when the conversation needs it and recovering more predictably after reconnects.
  • Narrative shotlists and action/media libraries are easier to scan, with grouped shot cards, video previews, action catalog filtering, and recommended image and video models.

Fixed

  • Reopening a running simulation is less likely to create a parallel chat or 3D run instead of returning to the existing session.
  • Stopping, pausing, and reconnecting simulations now update visible run status more reliably across the launcher and chat surfaces.
  • Project duplication and deletion flows now give clearer feedback while the workspace refreshes around the changed project.

WebGL streaming polish, richer share cards, and pricing fixes

Shared pages now look better when you post them elsewhere, live simulation chat is easier to follow, and pricing details are clearer and more accurate.

Version 1.5.3

April 8, 2026

New

  • Shared creator, project, character, and chat pages now produce richer preview cards when you post them in social apps, messages, or other link-friendly surfaces.
  • Live simulation logs now make it easier to tell who is actively responding, what is still in progress, and how the conversation is unfolding during a run.
  • Reference image workflows now give you a faster way to reuse recent media while working on a project.

Improved

  • WebGL simulation playback is more stable, with smoother run controls and clearer live updates while agents are thinking or acting.
  • Public creator, share, and discovery pages use cleaner language and a more consistent presentation for shared projects.
  • Pricing and annual-savings details are now clearer and better aligned with what you actually see in checkout.

Fixed

  • In-progress chat updates stay readable more often instead of disappearing or showing incomplete fragments.
  • Busy simulation moments with multiple overlapping actions now display more cleanly in live views and logs.
  • Shared pages and preview images fail less often across different environments and link previews.

Public project storytelling, mobile cleanup, and better media workflows

Publishing and sharing public projects now includes narrative snapshots and stronger featured moments, the workspace behaves more cleanly on smaller screens, and reference and media workflows are faster to use.

Version 1.5.2

April 3, 2026

New

  • Public project publishing now lets you include a narrative snapshot from the default plot, choose one narrative image or video, and decide which shared chat moment leads the public page.
  • Public project pages now show that narrative section alongside clearer creator, cast, and featured-scene storytelling so visitors get context faster.
  • Reference image and reference video uploads now create the right narrative assets directly, so source material can enter a project without first attaching it to a storyboard or shot.

Improved

  • Explore, share, and publish surfaces now lean into project framing with cleaner public cards, stronger discovery copy, and easier share actions from the publish flow.
  • Simulation, chat, creation, and world-selection screens now adapt more cleanly to phones and narrower desktop layouts, with better spacing, wrapping, and compact controls.
  • The world media library is easier to scan and act on, with clearer browsing modes, stronger usage context, and faster edit-focused entry points for compatible assets.

Fixed

  • Featured moments on public project pages now honor the explicitly selected chat moment instead of drifting to an automatically chosen highlight.
  • External Meshy-hosted assets now load more reliably through the media proxy, with better handling for stricter upstream access checks.
  • 3D model previews and small-screen message layouts now fail more gracefully, reducing broken previews and overflowed metadata.

Embodied movement setup, cleaner streaming chat, and a simpler launcher

You can now define movement and conversation actions more explicitly, prepare WebGL runs with clearer setup guidance, and read agent chat without duplicated or noisy streaming messages.

Version 1.5.1

April 2, 2026

New

  • Actions now support explicit type and target settings, so you can mark an action as conversation or movement and direct it toward a person or a location when that matters.
  • World-building flows now surface these action settings directly while creating actions or assigning them to agents, with inline guidance for what each choice means.
  • The simulation launcher now calls out missing setup for embodied runs, including 3D character readiness, location coverage, and the movement and conversation actions a world still needs.

Improved

  • The launcher layout is cleaner and easier to scan, with a more focused start flow and working-plot controls that stay accessible while you set up a run.
  • The WebGL simulation view now includes a resizable split between the embodied scene and the lower utility panel, making it easier to balance the scene, logs, and inspector.
  • Sending a message from the embodied simulation can now start the run automatically when needed, so the first turn is less likely to stall during setup.

Fixed

  • Agent chat streaming is less likely to show duplicate or mismatched in-progress messages when tool calls and final logs arrive out of order.
  • In-progress tool calls now render more quietly, reducing visual clutter while an agent is still thinking or acting.
  • Movement-driven animations in the embodied view resolve more consistently when an action is marked as movement instead of relying only on legacy action names.

3D characters, richer world discovery, and smoother simulation setup

You can now build and manage 3D characters for agents, browse public worlds with clearer context, and move through simulation setup and resume flows with less friction.

Version 1.5.0

April 2, 2026

New

  • Agents can now have a dedicated 3D character workflow with text-to-3D and image-to-3D generation, uploaded models, version history, and preview-ready rigged assets.
  • 3D characters can generate animation sets automatically from agent actions or use manually selected motions, with action-to-animation mapping for runtime behavior.
  • Public worlds now surface featured moments, creator attribution, and cast previews so it is easier to tell what a world is about before you open it.

Improved

  • Explore, creator, and public world pages are more cinematic and easier to scan, with stronger cards, clearer overlays, and better use of cover art.
  • Simulation launch and resume flows now do a better job explaining each mode, guiding setup, and showing recent runs without overwhelming the page.
  • The main landing experience now points more directly to public exploration and creative development workflows instead of burying the entry points.

Fixed

  • Agent chat session state is more resilient during restarts and rapid view changes, reducing cases where stale state could interfere with a run.
  • Public world highlights now prioritize the selected featured moment more reliably instead of falling back to a less relevant line.
  • Simulation and WebGL loading, controls, and resume behavior are more consistent across the latest workspace flows.

Telegram replies, clearer LLM credit usage, and smoother sharing

You can now connect Telegram to receive and reply to world messages, see LLM credit usage more clearly, and open world sharing tools more directly from the workspace.

Version 1.4.0

March 28, 2026

New

  • Settings now include Telegram setup for direct chats, with connect links, status, and test messages.
  • Telegram replies and quick-action buttons can now route back into the relevant simulation so conversations can continue outside the browser.
  • World actions can now send Telegram messages to the linked user when a world needs to notify someone directly.

Improved

  • Usage totals now surface LLM generation credits and estimated LLM cost more clearly alongside the rest of your credit tracking.
  • World setup now includes a direct prompt to open sharing tools when a world has not been published yet.
  • Public world links and social cards resolve more reliably when shared across environments and external platforms.

Fixed

  • Agent chat startup is more reliable when the scheduler agent already exists, reducing setup failures in some worlds.
  • Room placement and simulation loading behave more consistently during agent-chat initialization and resume flows.

Guided world setup with sharper reference and media workflows

Starting a world is more directed, reference image generation is easier to manage, and simulation runs are clearer to scan and resume.

Version 1.3.1

March 26, 2026

New

  • World Designer and Generative Media Artist now ship with default catalog artwork, making curated assistants feel more intentional from the start.
  • Simulation launch now offers more guided entry points, including clearer paths for world setup, character imports, and creative exploration.
  • Narrative and reference-image workflows now share reusable media grids and schema-driven advanced fal.ai parameter controls.

Improved

  • Simulation run cards are easier to scan, with clearer type cues, start-time details, and resume context.
  • Reference and storyboard image flows now do a better job surfacing the right creative controls without overwhelming the first step.
  • Chat messages render generated media, MCP/tool output, and code details more cleanly across agent conversations.

Fixed

  • Plot lookups now behave correctly when a plot identifier is `0`.
  • Tagged catalog agents keep their intended default artwork instead of falling back to generic avatars.
  • Legacy generic chat simulation titles are recognized more reliably in the simulation flow.

A clearer media picker with better creative guidance

It is now much easier to choose the right image or video workflow for storyboards, references, polished shots, and edits.

Version 1.3.0

March 16, 2026

New

  • Media creation now gives you more options for quick drafts, polished images, guided edits, and motion work.
  • Storyboard, reference, shot, and finishing workflows now surface choices that better match the kind of creative work you are doing.
  • Commercial-use information is easier to spot before you commit to an image or video run.

Improved

  • Pickers in Narrative Designer and reference-image workflows are now organized by creative goal instead of one long list.
  • Each option includes a short recommendation so you can tell what it is best for before you choose it.
  • Selected options now give clearer guidance for first-pass ideas, image-led edits, continuity work, and final polish.

Fixed

  • New media options now appear more consistently across the app.
  • Usage labels and recommendations behave more predictably across generate, edit, motion, and reference workflows.

Safer accounts, clearer credits, and a faster action picker

You can now verify your email, manage active sessions, top up generation credits, and browse creative actions with clearer capability guidance.

Version 1.2.0

March 16, 2026

New

  • New account verification flow with resend support, plus easier password reset and recovery.
  • Security settings now include active session management, password changes, and self-serve account deletion.
  • Billing now supports generation credit top-ups with a clearer view of balances and usage.

Improved

  • Action selection is grouped by capability, with better summaries for narrative, media, and tool actions.
  • Narrative, billing, and settings screens have been refined to make common workflows easier to follow.
  • Social media import and content generation flows are more polished and predictable.

Fixed

  • Resolved several signup, verification, and credential handling regressions.
  • Fixed generation and deletion issues that could interrupt media and content workflows.
  • Creative tools and integrations now behave more reliably in edge cases.

Narrative Designer expands into storyboards and reference assets

Narrative planning is now more complete, with richer storyboard structure, plot tooling, and asset reference workflows inside the app.

Version 1.1.0

January 18, 2026

New

  • Narrative Designer now supports deeper plot, shot, and storyboard planning workflows.
  • Reference images and media links are easier to attach to narrative work as you iterate.

Improved

  • Asset handling and narrative generation flows are more connected across the workspace.
  • Frontend detail panels were refreshed to better support narrative editing.

Fixed

  • Ownership and deletion support was tightened up around shared app entities.
  • Media creation flows are more reliable from start to finish.