What problem does it solve? Coordinating multiple AI agents for complex tasks usually requires external orchestration frameworks, custom code, and infrastructure. OpenProse lets you write structured .prose programs that the AI session itself executes as a virtual machine, spawning subagents, managing state, and handling control flow without any external dependencies. ## Core Features & Use Cases - Program Execution: Run .prose files locally, from URLs, or from the p.prose.md registry, with the AI embodying the OpenProse VM and spawning real subagent sessions. - Compilation and Validation: Validate .prose syntax against the full language grammar without executing, catching errors like undefined agents or invalid models. - Flexible State Management: Choose between filesystem state (default), in-context state, or experimental SQLite and PostgreSQL backends for persistence and resumption. - Use Case: Write a program that runs three code reviewers in parallel, loops until the code passes review, and escalates to a persistent orchestrator agent on failure—then execute it with a single prose run command. ## Quick Start Run the hello world example by asking the AI to execute prose run examples/01-hello-world.prose.
