An adversarial swarm engine/v0.2 · phase 2 preview

Upload your tokenomics.
Stress-test the future.

Drop a whitepaper or a pre-built scenario. Sim Wars spawns from 8 to 5,000 LLM-powered adversaries — whales, governance attackers, MEV bots, sybil swarms — and lets them attack your design until it survives, or speedruns a death spiral.

Run the simulation. Find the failure mode. Ship the fix.

Continue

System status

Ready

Engine is idle. Pick a pre-built scenario or upload your own whitepaper — Sim Wars extracts tokenomics and seeds a fresh adversarial run.

OpenRouter-backedcheap preset for agents · quality preset for the report

Up to 5,000 agentsserver-side roster expander · veToken / LUNA / balanced presets

01 / Tokenomics source

Workflow sequence

01Seed extractionTokenomics parameters parsed from PDF, GitHub, or raw markdown via OpenRouter preset.
02Roster expansionServer-side expander spawns 1–5,000 adversarial personas from veToken / LUNA / balanced archetypes.
03Live simulationPer-tick LLM decisions batched in parallel. Stake / propose / vote land on Solana with real tx signatures.
04Failure reportResilience score, attack timeline, and parameter recommendations after the run.

02 / Adversary roster — 20 agents(12 archetypes · LUNA-style cascade)● ready

ROSTER PRESET

AGENT COUNT

1820501002505001,0002,5005,000

≈ 0.13 USD/30-tick runlocalnet OK

WHALE_01Whale

FARMER_01Yield Farmer

DEGEN_01Retail Degen

WHALE_02Whale

GOV_01Gov Attacker

HOLDER_01Long-Term Holder

HOLDER_02Long-Term Holder

FARMER_02Yield Farmer

GOV_02Gov Attacker

SYBIL_01Sybil

MEV_01MEV Bot

FARMER_03Yield Farmer

DEGEN_02Retail Degen

DEGEN_03Retail Degen

ARB_01Arbitrageur

TREASURY_01Treasury

LP_01LP Provider

ANALYST_01Analyst

INSIDER_01Insider

PANIC_01Panic Seller

2× Whale

3× Yield Farmer

3× Retail Degen

2× Gov Attacker

2× Long-Term Holder

1× Sybil

1× MEV Bot

1× Arbitrageur

1× Treasury

1× LP Provider

1× Analyst

1× Insider

1× Panic Seller

03 / Tick parameterseditable

MAX TICKShow long the sim runs (each tick = one LLM round)TICK INTERVAL (ms)0 = run as fast as the LLM responds

ON-CHAIN MODE

Deploy mints + AMM pool + staking + governance to the configured Solana cluster, then run. Each agent gets a real keypair + ATAs. Requires deployer SOL (≈ 0.5 + 5×agents). Without this, the sim runs against an in-memory AMM only.

openrouter keynot set — required for live runs

POST /api/sim

Upload your tokenomics.Stress-test the future.

Ready

Upload your tokenomics.
Stress-test the future.