Open Envelope
an open schema for defining AI agent teams
Details
- External ID
- 48315016
- Source
- HN
- Company
- —
- Product
- Open Envelope
- Website domain
- openenvelope.org
- Launched
- May 28, 2026
- Cohort
- —
- Upvotes
- 52
- Upvotes percentile
- 0.8432956381260097
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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.
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- schema standard for ai agent teams
- Manually corrected
- False
Could you build this?
Yes It is a declarative JSON Schema specification accompanied by documentation and a static website.
Discussion
13 comments analyzed.
Competitors mentioned: Claude Code dynamic workflows, Terraform, Pulumi, CDK
Concerns raised: Runtime hazard when multiple agents read/update same artifact without coordination, Vendor lock-in if schema tied to specific model/runtime, Tool-level access scope not first-class, only agent-level HTTP access, Trigger logic insufficient for XOR relationships and plan-solving scenarios, Missing tool invocation controls like at-most-once semantics
Feature requests: Recursive trigger conditions for complex approval logic, Tool-defined access scopes independent of agent level, At-most-once invocation control for quality of service, Function-level tool definition layer with first-class access policies, Per-tool invocation semantics and controls
Competitors
Other products that read as similar to this one — 297 launches clear the similarity bar, closest 8 shown.
Attention rank: #57 of 298 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 206 days after the earliest competitor.
- Orloj · hn · 2026-03-26 · 20 upvotes · similarity 0.49
- Open Agent Desktop · ph · 2026-09-28 · 1 upvotes · similarity 0.48
- AgentML · hn · 2025-11-03 · 5 upvotes · similarity 0.47
- ZeroID · hn · 2026-04-08 · 7 upvotes · similarity 0.47
- Agent Passport · hn · 2026-02-21 · 14 upvotes · similarity 0.47
- AgentArmor · hn · 2026-03-14 · 10 upvotes · similarity 0.45
- OpenSOP, We got tired of agents lying to us, so we built them a harness · hn · 2026-06-03 · 5 upvotes · similarity 0.45
- Open Agents · ph · 2026-04-14 · 161 upvotes · similarity 0.45
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.