STRATUS X1
A World Model to unlock the next generation of Agents.
while LLMs predict tokens..
Stratus predicts worlds
STRATUS is a world model built for agents. It sits above LLMs, not replacing them, supplying the predictive intelligence needed for reliable planning, action, and coordination.
Same SDK.
Smarter agent.
Drop in. Don't look back.
One line. Same SDK.
import OpenAI from "openai"const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY})Change: baseURL + Stratus API key
import OpenAI from "openai"const client = new OpenAI({ apiKey: process.env.STRATUS_API_KEY, baseURL: "https://api.stratus.run/v1"})Works with OpenAI, Anthropic, Gemini, and any compatible API.
Agents that see
before they act
STRATUS X1 predicts state transitions in embedding space, giving agents the foresight to simulate, plan, and validate before execution. Task success doubles. Real autonomy emerges.
WebArena Task Success Rate
Real-world web automation tasks. STRATUS X1 boosts navigation, interaction, and completion rates.
HotpotQA Performance
Multi-hop reasoning benchmark. STRATUS X1 lifts both EM and F1 by simulating outcomes before responding.
Increases completions, lowers token usage, and provides near-zero latency.
not words..
Six ideas. One engine.
STRATUS X1 is built on a chain of interlocking concepts — each one a prerequisite for the next. Together they form the first practical world model for production agents.
World Model
Stratus X1 builds a continuous representation of the environment — not next-word probabilities, but next-state predictions in embedding space.
JEPA
The Joint Embedding Predictive Architecture learns structured representations by predicting the abstract embedding of a target state — not the raw pixels or tokens.
Prediction
Before the agent touches the environment, X1 forecasts outcome embeddings across candidate action sequences — converting blind execution into foresighted planning.
Simulation
X1 rolls out multiple futures in latent space simultaneously. Each branch is a simulated world — explored in under 10 ms, before a single real action is taken.
Comparison
A learned value function scores each simulated trajectory against the task objective. The agent selects the highest-ranked path — not the first plausible one.
Validation
After execution, X1 verifies the resulting state matches the predicted embedding. Drift triggers re-planning — turning one-shot agents into self-correcting systems.
Infrastructure
Bring Nothing,
Build Everything
No provider signups. No API keys to juggle. Hit any OpenAI, Anthropic, or Google model instantly — Formation routes it.
import { StratusClient } from '@formthefog/stratus-sdk-ts';
const client = new StratusClient({
apiKey: process.env.STRATUS_API_KEY!,
});
const response = await client.chat.completions.create({
model: 'stratus-x1ac-base-gpt-4o',
messages: [
{ role: 'system', content: 'Current state: Homepage. Search box visible.' },
{ role: 'user', content: 'Search for wireless headphones' }
]
});
console.log(response.choices[0].message.content);
console.log(response.stratus?.overall_confidence);
console.log(response.stratus?.action_sequence);The native SDK exposes response.stratus — action sequences, confidence scores, and world-model metadata not available through third-party SDKs.
Every API response includes key_source and formation_markup_applied — fully transparent billing.