Stratus X1

STRATUS X1

A World Model to unlock the next generation of Agents.

Loading...
The Agentic World Model Layer

Stratus predictsdigital 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.

Compatible with:ClaudeGPTOpenClawMiniMaxKimiGeminiand more
STRATUS X1 World Model

Same SDK.
Smarter agent.

Compatible with all major LLMs and frameworks
OpenAI SDK · With Stratus
import OpenAI from 'openai';const client = new OpenAI({  baseURL: 'https://api.stratus.run/v1',  apiKey: process.env.STRATUS_API_KEY});const response = await client.chat.completions.create({  model: 'stratus-x1ac-base-claude-sonnet-4-5',  messages: [    { role: 'user', content: 'Plan a route through 20 cities' }  ]});

Drop-in compatible with your existing SDK. Just change the baseURL and use your Stratus API key.

Language:
STRATUS X1 Model Design

World Model Architecture

STRATUS X1 is built on a chain of interlocking concepts, each one a prerequisite for the next. Together they form the first production world model for agents.

01
State over tokens

World Model

Where LLMs predict tokens, Stratus X1 predicts states. It encodes the current environment into a dense embedding and learns how the world changes when an agent acts.

02
See before you act

Prediction

Before the agent touches the environment, X1 forecasts outcome embeddings across candidate action sequences converting blind execution into foresighted planning.

03
Branch possible worlds

Simulation

X1 rolls out multiple futures in latent space simultaneously. Each branch is a simulated digital world, explored in under 10 ms, before a single real action is taken.

04
Rank trajectories

Comparison

A learned value function scores each simulated trajectory against the task objective. Enabling agents to move along the highest-ranked path, not the first plausible one an LLM generates.

05
Commit with confidence

Validation

Every action is followed by a prediction check. If the outcome doesn't match what X1 expected, it triggers a new planning cycle so agents recover from errors instead of compounding them.

06
Built to evolve

Living Model

Unlike static models, Stratus X1 continuously learns through anonymized interaction traces. Allowing the model to adapt over time without ever storing inference data or sensitive information.

Infrastructure

Latent Encoder
Compresses observations into compact state vectors
Trajectory Planner
Searches action sequences in embedding space
Value Network
Scores candidate paths against task objectives
State Monitor
Tracks drift between predicted and actual states
Context Fusion
Merges tool outputs, memory, and observations
Replay Buffer
Stores successful trajectories for few-shot transfer
Benchmarks

Agents that plan 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.

Claude Sonnet 4
+105%
Baseline
20%
With X1
41%
GPT-4o
+100%
Baseline
17%
With X1
34%
Llama 4 Scout
+150%
Baseline
12%
With X1
30%
DeepSeek V3
+93%
Baseline
15%
With X1
29%

HotpotQA Performance

Multi-hop reasoning benchmark. STRATUS X1 lifts both EM and F1 by simulating outcomes before responding.

DeepSeek V3
Exact Match
+68%
37%vs62%
F1 Score
+48%
0.46vs0.68
GPT-4o
Exact Match
+55%
44%vs68%
F1 Score
+46%
0.54vs0.79
Claude Sonnet 4
Exact Match
+51%
41%vs62%
F1 Score
+57%
0.49vs0.77
Llama 4 Scout
Exact Match
+66%
35%vs58%
F1 Score
+56%
0.43vs0.67

Increases completions, lowers token usage, and provides near-zero latency.

0.0×
Task Success Rate
0%
Token Reduction
+0%
Exact Match Improvement
<0ms
Inference Latency
Predict worlds,
not words..

X1