prose

Orchestrate durable multi-agent workflows with state and evidence recording.

Updated Aug 27, 2026

Search Tags:#verification #multi-agent #orchestration #state-management #vm #ai-workflow #openprose

Ready to run

npx skills add https://github.com/rebootix-research/viki-clow --skill prose-rebootix-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/rebootix-research/viki-clow/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/rebootix-research/viki-clow --skill prose-rebootix-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenProse provides a programmable VM-first model to orchestrate durable, auditable AI workflows by spawning subagents, managing state, and recording evidence.

Core Features & Use Cases

Spawns sessions and coordinates parallel and sequential workflows across agents.
Maintains memory for persistent agents and tracks execution state for resumption and proofs.
Supports multiple backends (filesystem, in-context, SQLite, PostgreSQL) for durable workflows and cross-project collaboration.
Use cases include building automated pipelines, captain's-chair orchestrations, and production-grade agent workflows with traceable evidence.

Quick Start

Run a minimal OpenProse example such as prose run examples/01-hello-world.prose to see the VM orchestrate a simple session.

Frequently Asked Questions about prose

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I orchestrate durable multi-agent workflows that can be resumed after interruption?▼

Multi-agent workflow orchestration uses a VM-first model to coordinate sessions, manage state, and record evidence so long-running operations can resume and provide auditable proofs.

What is the best way to manage state and memory for persistent AI agents across sessions?▼

State management for persistent AI agents is handled through multiple backends including filesystem, in-context, SQLite, and PostgreSQL, allowing durable workflows to maintain memory and track execution state for cross-project collaboration.

Does OpenProse support parallel execution for subagents in automated pipelines?▼

Parallel execution for subagents is supported natively, enabling the VM to spawn sessions and coordinate concurrent workflows across multiple agents while maintaining memory and recording evidence for production-grade operations.

How do I run a minimal multi-agent orchestration example to test the VM?▼

Running a minimal orchestration example involves executing a command like prose run examples/01-hello-world.prose, which demonstrates how the VM orchestrates a simple session and coordinates basic agent workflows.

What are the requirements for Skill discovery and frontmatter in OpenProse workflows?▼

Skill discovery in OpenProse workflows requires a SKILL.md file at the root directory and a defined frontmatter containing name and description, while optional resources in scripts/, references/, and assets/ load as directed by SKILL.md.

Can I use SQLite or PostgreSQL backends for auditable AI workflow state tracking?▼

SQLite and PostgreSQL backends are fully supported for auditable AI workflow state tracking, providing durable storage that enables cross-project collaboration and verifiable evidence recording for long-running agent operations.