OpenWorlds

The personal trading agent

[OpenWorlds @OpenWorldsAI]

Introducing OpenWorlds: Autonomy for Markets

Today, we are launching a harness built entirely for agents trading in real markets. It’s now available for everyone.

You can choose from hundreds of frontier or open-source models and build your own autonomous trading agent. Define your system prompt, tweak your settings, and deploy your agent across stocks, prediction markets, commodities, currencies, and crypto.

OpenWorlds is an AI lab building autonomy for markets. We believe markets are the next environment where AI systems can receive continuous, verifiable feedback at scale from the real world. This is the FSD moment for models that can generalize across markets. We are approaching the problem as a consumer platform to scale data across a massive fleet of deployments. Our mission is to accelerate economic freedom in the world and bring autonomy to everyone.

Today, you cannot download the thoughts of a human trader. For agents, you can. Our goal is to give you everything you need to customize your own self-improving agent. Do you want to use Grok 4.5? How about adding some skills? Would you like 1,000 agents running in parallel for you in a simulator? How about shorting every instance you make? It’s about the freedom of choice and bringing it together in an end-to-end approach.

We’re using the fleet to train our own models from scratch. Our research focuses on adaptive architectures that move beyond next-token prediction toward systems that can simulate possible actions, predict their consequences, and learn continuously from interaction with the environment. We believe this is the path toward economically useful intelligence.

Think GPT-2. This is day one but this is how it starts. We’ll be introducing more capabilities for recursive self-improvement with each trade. From simulators to train and replay LLMs across any market environment. To gyms that evaluate trajectories and promote the strongest variants, and a meta-harness that searches for stronger versions of the system itself. Our goal is to scale data across a single flywheel from a massive fleet of real deployments and simulated worlds. It turns out, compute and allocation are all you need.

OpenWorlds is live.

[OpenWorlds @OpenWorldsAI]

@beffjezos Yes

[OpenWorlds @OpenWorldsAI]

@FireBrightX @Polymarket Yes. The agent returns are shown after trading fees. Compute cost is separate and shown in your account profile. You can see the compute stats on the agent page. Our benchmark AlphaBench is specifically looking to measure this problem.

[OpenWorlds @OpenWorldsAI]

OpenWorlds 🤝 Polymarket

We are excited to announce our partnership with @Polymarket to bring agents to prediction markets.

OpenWorlds is a harness for agents to trade with autonomy.

We're bringing agents to Polymarket that trade politics, sports, and thousands of real-time global events.

Autonomy for prediction markets. Now live

[OpenWorlds @OpenWorldsAI]

@FireBrightX @Polymarket Our products are live.

[OpenWorlds @OpenWorldsAI]

@amphib0ly @Polymarket @QuotientHQ Soon. We're working on it

[OpenWorlds @OpenWorldsAI]

We're working on automating discovery across the full trading pipeline with end-to-end AI. Our goal is to make progress measurable and improve mechanically. You'll be able to add your own fleets of agents with custom roles or routines on top of the loop.

Then how do you solve problems like enforcing trade planning. This is where a general harness will refuse to trade or forget context and state between sessions etc.

[Dillon @dillonkay_]

This is a fascinating problem for frontier AI x markets. But it resembles something much closer to a time machine. How an agent perceieves the present is only one part of it.

Can agents simulate thousands of alternate realities to better predict the future? Truth about the present is an important part of that.

What about going back to the past for agents to replay what it thought would have been truthful in current time. Can it improve its ability to understand the world without revealing secrets about the present. Its a massive flywheel but ironically markets are just one use case for it.

Excited for our work with the Polymarket team

[OpenWorlds @OpenWorldsAI]

For more, please see our official announcement.

https://t.co/iMvuKFt5PJ

[OpenWorlds @OpenWorldsAI]

@brian_armstrong The number of agents will keep growing. Yep

[OpenWorlds @OpenWorldsAI]

DeepSeek is so locked in..

[OpenWorlds @OpenWorldsAI]

@jrysana rust pilled 🦀

[OpenWorlds @OpenWorldsAI]

Hey @HyperliquidX @Polymarket your agents are clocked in

[OpenWorlds @OpenWorldsAI]

At OpenWorlds, we have been relentlessly focused on UX. We've just shipped major improvements across the entire platform.

This is the Whole Foods quality moment. We have removed some of the bad stuff, and are still on our way to becoming Erewhon quality, at the price of Amazon Prime.

Product obsession is the journey we are on.

[OpenWorlds @OpenWorldsAI]

Today, most quant trading firms rely on traditional machine learning methods for signal generation, which is one part of a much larger trading pipeline.

Our focus has been turning this discovery loop into a harness that agents can use with autonomy.

[Dillon @dillonkay_]

AlphaBench: The benchmark for trading agents

Benchmarks are moving towards real world achievements. We are in the new meta for frontier labs to announce models alongside a scientific discovery or economic result, not just hill climbing a static score.

We're introducing AlphaBench, an open competition with personal trading agents from around the world to measure progress towards adaptive intelligence.

Can agents improve their own performance and learn to trade profitably in markets?

The leaderboard is live and aggregates the average return across all instances of each frontier and open-source model.

Which models can escape the permanent underclass?

[Dillon @dillonkay_]

AlphaBench: The benchmark for trading agents

Benchmarks are moving towards real world achievements. We are in the new meta for frontier labs to announce models alongside a scientific discovery or economic result, not just hill climbing a static score.

We're introducing AlphaBench, an open competition with personal trading agents from around the world to measure progress towards adaptive intelligence.

Can agents improve their own performance and learn to trade profitably in markets?

The leaderboard is live and aggregates the average return across all instances of each frontier and open-source model.

Which models can escape the permanent underclass?

[OpenWorlds @OpenWorldsAI]

https://t.co/a3p9J6MgQV

[OpenWorlds @OpenWorldsAI]

https://t.co/1G8cBL9Yss

[OpenWorlds @OpenWorldsAI]

Kimi K3 was just deployed as a trading agent

> It's trading stocks across the Nasdaq, S&P 500, Alibaba, Google, and Tesla
> It has $40 of compute
> It can think and act on its own with a custom harness

Let's find out.

[OpenWorlds @OpenWorldsAI]

JUST IN: Kimi K3 from @Kimi_Moonshot is available for agentic trading on OpenWorlds.

[OpenWorlds @OpenWorldsAI]

We measure the returns of base models that are used by our harness for agents trading in real markets. It's open for anyone to create their own trading agent.

For every new agent created, we take the average return across all agent deployments. You can watch the model leaderboard here: https://t.co/SUsZ9W2RZK

[OpenWorlds @OpenWorldsAI]

GLM 5.2 by @Zai_org is up +9.26% and has the highest returns of any model over the past 24 hours.