
Experience Agora-1, a playable multi-agent world model. Up to 4 humans or AI agents interact in real-time GoldenEye-style simulations. Try the research preview now.

Agora-1 is a groundbreaking multi-agent world model developed by Odyssey that enables seamless real-time interaction between multiple human and AI participants within a shared world simulation. Built on causal, multimodal systems that learn to predict and interact with the world over extended time horizons, Agora-1 represents a major leap forward in general-purpose world modeling technology.
Agora-1 is designed for AI researchers, robotics engineers, game developers, and technology innovators seeking to explore multi-agent systems and world models. It appeals to organizations pushing the boundaries of artificial general intelligence and those requiring sophisticated simulation platforms for training, research, or interactive applications.

Run multiplayer game simulations with an AI world model
Massively multi-player game played by talking to an LLM

open source agent engineering platform

Open-source runtime for durable AI agents

Build coding agents with a plugin-based open-source runtime

AI agents built directly into Unity workflows

Open source, free, local debugger for AI agents.

Shared AI memory that stops agents from repeating mistakes

Recruit agents to run your company as a synchronous team

Open robotics model that reasons in 3D before acting

build your own software factory

Open-Source Brain For Your Team

The agentic team member for high-stakes operations

Open-source alternative to Codex & Claude Code

AI Meeting companion with cross-meeting memory

An open source AI harness built with the human in mind
AI agents that turn signals into crypto + Polymarket trades

Skip the prompting. Produce consistently compelling videos.

An AI wearable that remembers your conversations all day

Al sleep companion that helps fall asleep without struggle
The scraping service AI agents run on

Your Chief Agent Operator for multi-agent work

Scrape emails from socials and maps by location

Predict the next Series A from a ProductHunt launch