Introducing ARP: capability-oriented infrastructure for reliable agentic systems
ARP combines COP, ARP Standard v1, and JARVIS to deliver bounded, auditable agentic workflows.
Blog
Updates, release notes, and deep dives from the ARP maintainers.
What we publish
We publish:
- Release notes: What shipped, what changed, and why.
- Deep dives: Bounded orchestration, artifacts, policy checkpoints, conformance.
- Adoption guides: How to adopt incrementally, from “wrap one capability” to platform-scale.
- Ecosystem notes: How ARP composes with other protocols and stacks.
Start here
If you’re new, these posts establish the core mental model.
Introducing ARP: capability-oriented infrastructure for reliable agentic systems
ARP combines COP, ARP Standard v1, and JARVIS to deliver bounded, auditable agentic workflows.
ARP in 10 minutes: one run, five artifacts
A hands-on walkthrough of a single run that produces bounded candidate menus, enforceable constraints, policy decisions, and a durable event timeline.
ARP Standard v1: what’s standardized — and what’s intentionally not
ARP Standard v1 defines the contracts and artifacts for bounded, auditable capability execution—without standardizing planner internals.
Latest posts
-
-
ARP in 10 minutes: one run, five artifacts
A hands-on walkthrough of a single run that produces bounded candidate menus, enforceable constraints, policy decisions, and a durable event timeline.
-
ARP Standard v1: what’s standardized — and what’s intentionally not
ARP Standard v1 defines the contracts and artifacts for bounded, auditable capability execution—without standardizing planner internals.
-
COP: Capability-Oriented Programming for production agentic systems
COP treats capability reliability as the unit of engineering. Build around what nodes can consistently do, prove it with evaluation, and reuse it safely.
-
JARVIS: why a standard needs a reference implementation
JARVIS is the first-party OSS reference stack for ARP Standard v1. Run it end-to-end, inspect artifacts, and use it as a baseline for your own implementations.
-
ARP FAQ: what it is, what it isn’t, and how to adopt it
The questions we keep hearing: why ARP, how it relates to frameworks and tool protocols, what’s standardized, and how teams adopt incrementally.
-
Interoperability first: how ARP composes with MCP, A2A, and existing stacks
ARP treats external protocols and runtimes as capability sources: wrap them as NodeTypes, bound them with CandidateSets, and govern them with policy checkpoints.
Want to contribute?
We’re happy to review integration writeups, implementation notes from building conformant components, and case studies.