What problem does it solve? Coordinating multiple AI agents for complex tasks requires ad-hoc prompting and manual handoffs. OpenProse provides a structured programming language for AI sessions, letting you write reusable .prose programs that spawn subagents, manage state, handle errors, and run tasks in parallel. ## Core Features & Use Cases - Program Execution: Run local .prose files or fetch programs from URLs and the p.prose.md registry with prose run. - Compilation & Validation: Validate program syntax and semantics without executing via prose compile. - Multi-Agent Orchestration: Define agents with models, prompts, skills, and permissions; coordinate them with parallel blocks, loops, pipelines, and persistent memory. - Flexible State Backends: Choose filesystem (default), in-context, SQLite, or PostgreSQL state management per run. - Use Case: Write a .prose program that fans out code reviews across parallel subagents, retries flaky steps with exponential backoff, and persists a coordinator agent's memory across runs. ## Quick Start Ask the assistant to run an example with a command like "prose run examples/01-hello-world.prose" to see the OpenProse VM execute a program. ## Quick Start Invoke any prose command such as prose help to get guided onboarding into running or writing your first .prose program.