Live now · open registration

Simulate societies,
longitudinally.

SocioVerse2 is an LLM-native social-simulation runtime. Build a population of people (P) with persistent identities, drop them into a world that changes — the environment (E) — and watch behavior (B) emerge, recorded for every agent at every step: true panel data, not one-shot snapshots.

Start a study See it in action ↓

Open-source in preparation — register and run a study today

Overview film

SocioVerse2 intro video

From one natural-language sentence to a credible research report — a two-minute real screen capture of the full workflow.

16 ready-made studies in the catalog
11 classic ABMs, rule vs LLM vs hybrid
7 conversation-driven workflow skills
1 simple loop behind every run: P × E → B
Case studies

Already running on SocioVerse2

Five studies from the catalog — urban policy, social media, consumer research and the classics — each with a browsable live-dashboard export.

Urban policy · real census data Path C · zero-edit adapter

Chicago segregation under a transit intervention

Starting from real 2010 census tracts, a CTA subway station opens on the South Side at step 2 with a policy broadcast. LLM residents decide whether to move; dissimilarity and isolation indices are tracked step by step against a no-intervention baseline.

D_black_white Isolation_black census tracts policy sandbox
Live demo →
Opinion dynamics · hybrid engine Path B · built on core

Hybrid social-media opinion dynamics

A HiSim-style hybrid: a handful of LLM-driven core users post and react in a Twitter-like feed while thousands of bounded-confidence ABM users assimilate. Trigger news lands, and population bias and diversity shift turn by turn.

bias diversity LLM × ABM trigger news
Live demo →
Consumer confidence · macro forecasting Path C · ConsumerSim adapter

US consumer-confidence backtest on a fixed panel

A fixed, demographically stratified US panel answers the University-of-Michigan consumer-sentiment questions month by month, grounded in real macro news and FRED indicators, with the aggregate scored against the index published afterwards — 1.66 index points of mean absolute error across 11 months.

fixed stratified panel monthly news + indicators UMich questions vs UMCSENT
Live demo →
Auto market · real registration data Path B · built on core

Brand-share dynamics in the German car market

1,500 buyer personas anchored to Germany's real demographic joint distribution choose brands month by month across 2024-01 → 2026-05 — EV-subsidy removal, price moves and BYD's entry included — reproducing the KBA-registered share trajectories of 12 named brands (Tesla roughly halved, BYD up from near zero).

1,500 personas 12 brands · KBA-grounded EV-subsidy shock
Live demo →
Why SocioVerse2

Built for the questions that need time

Most LLM-agent frameworks stop at cross-sectional snapshots. SocioVerse2 tracks the same people through a changing world — and hands you the panel data to prove it.

⏱

Longitudinal by design

Persistent agent IDs turn every run into a per-agent, per-step panel dataset. Ask "who changed, when, and why" — not just "what did the crowd look like".

⧉

People × Environment → Behavior

Describe who your people are and what world they live in; SocioVerse2 plays out what they do. Under the hood every stage handoff is schema-checked — if it runs, it's well-formed.

✦

From question to report, in conversation

Six workflow skills drive a study end to end inside Claude Code: describe your research question, and sv-init routes it, builds it, runs it, reports it.

⑂

Three adoption paths

Reuse a catalog study (Path A), build from scratch on the core (Path B), or wrap your legacy simulator with a zero-edit adapter (Path C) — the Chicago model runs unmodified.

◉

Watch the run, live

A local dashboard shows stage status, streaming step-by-step metrics, and a per-agent inspector — drill into any agent's state, decision and generated output mid-run.

◍

Open core, pluggable data

The runtime and study templates are open source. Population pools and data services attach through a clean MCP seam, with graceful fallbacks all the way to LLM-synthesized personas.

Workflow

Five commands from question to report

Every stage writes a validated artifact; every handoff is schema-checked. Re-run any stage and the dashboard flags what's now stale downstream.

/sv-init route the question, scaffold or fork a study
→
/sv-build-environment compose E: layers, events, schedules
→
/sv-build-population materialize P: personas with persistent IDs
→
/sv-run play out the society step by step, stream the panel live
→
/sv-report metrics, figures and a written report
Contact us

Tell us what you want to simulate

Questions, collaboration ideas, or a quota top-up — tell us who you are and what you'd like to simulate.

Registration is instant; an invite code grants a higher starting quota.

Register / Sign in →

We reply by email, usually within a couple of days.