ComingUp
Gallery
About
Built an open JSON Schema for defining AI agent teams.Multi-agent systems are becoming a real deployment pattern — not single assistants, but teams with roles, handoffs, and human checkpoints. But there's no shared way to define one that travels across frameworks. Every implementation is scattered, locked to whichever tool you picked first. Built the schema to fix that.The schema lives at schema.openenvelope.org and is registered in SchemaStore, so if you drop a .envelope.json file in VS Code you get autocomplete and validation without installing anything. It's also on npm as @openenvelope/schema if you want to validate programmatically.The spec covers: agent definitions (role, prompt, model, access policy), supervisor/sub-agent hierarchy, human-in-the-loop gates, pipelines, schedules, and secrets/variables that get injected at deploy time. Access policies let you declare exactly which hosts each agent can call — the runtime enforces this at the network level, not in the prompt.The goal is a portable definition format — define a team once, any compatible runtime can execute it. Similar to how Dockerfiles describe a container without being tied to a specific host. There's a managed runtime at openenvelope.org but the schema is Apache 2.0 and anyone can implement it.Happy to answer questions on any part of the spec — especially interested in feedback from people who've built multi-agent systems and have opinions on what's missing.
Comments (9)
Standardizing multi-agent orchestration is sorely needed, right now everyone's rolling their own ad-hoc configs and it's a mess 🙃. The checkpoint concept is smart, though the real challenge will be getting frameworks to actually adopt a shared schema instead of paying lip service to interoperability.
Standardizing agent team configs makes sense conceptually, but this feels premature. The space is still figuring out basic patterns, what handoffs look like, how context sharing should actually work, where human checkpoints add value versus just friction. Locking any of that into a schema before those patterns settle means it'll either be too generic to be useful or too opinionated to get adoption. Also JSON Schema tends to get verbose fast, which doesn't help with iteration speed when you're still exploring.
Unclear how this gains traction without major framework adoption.
schema without runtime validation is just documentation with extra steps
what's the revenue play here, paid tooling on top?
who's actually deploying multi-agent teams rn tho
another schema nobody will adopt when langgraph and crewai already shipping
finally bringing structure to the agent team chaos
agent handoffs need a standard json format
