What problem does it solve? Coordinating multiple AI agents for complex tasks requires ad-hoc prompting and manual sequencing. OpenProse provides a structured programming language for AI sessions, letting you define reusable multi-agent workflows in .prose files that a Prose Complete system executes as a virtual machine. ## Core Features & Use Cases - Program Execution: Run .prose files with prose run, spawning subagent sessions with sequential, parallel, loop, and pipeline control flow. - Compilation & Validation: Validate program syntax and semantics with prose compile before execution. - State Management: Choose between filesystem, in-context, SQLite, or PostgreSQL state backends, with persistent agents that retain memory across runs. - Use Case: Write a .prose program that fans out code reviews across parallel agents, retries failed sessions with exponential backoff, and synthesizes results into a final report. ## Quick Start Run the hello world example by asking the assistant to execute prose run examples/01-hello-world.prose.