# Envelope > Envelope designs your multi-agent workflow. Describe what you need, get a complete AI agent design — roles, skills, models, tools, and handoffs — and export without code. Full content index (writing, blog, docs, guides, pricing, tools, roles, library, schema, MCP): https://openenvelope.org/llms-full.txt Per-page Markdown: Append `.md` to any page URL to get a clean plain-text version, e.g. https://openenvelope.org/docs/schema.md or https://openenvelope.org/writing/composable-ai-thesis.md Envelope is where multi-agent workflows get designed before they get built. Non-technical stakeholders describe what they need in plain language; Envelope structures it into a complete AI agent design — roles, skills, models, tool access, and handoffs. The output is a structured, exportable spec — no code required to design, no ambiguity when handing off. ## Homepage [Envelope](https://openenvelope.org/): The multi-agent designer. Users describe their AI workflow in natural language; Envelope structures it into a complete AI agent design — roles, skills, models, tool access, handoffs, and access policies — which can be exported as a structured JSON spec. Free to start. Designs can be shared via read-only link, exported to JSON, or handed off to an engineering team for implementation. ## For agencies [Envelope for Agencies](https://openenvelope.org/agencies): Dedicated landing page for agencies — marketing, dev shops, and consulting firms — who want to design and deliver AI agent workflows to clients. Covers the three-step flow (design → spec → hand off to client IT), use cases by agency type, and the multi-client workspace model. Positioned as the multi-agent designer for agencies building AI retainers and recurring AI workflow deliverables. ## Pricing [Pricing](https://openenvelope.org/pricing) — [Markdown](https://openenvelope.org/pricing.md): All plans are free during beta. Plans: Free ($0 — 5 saved designs, canvas, JSON export, share link, MCP server access), Pro ($9/mo — unlimited designs, version history, REST API access), Team ($39/mo — collaborators up to 10 seats, GitHub publish, org-wide design library), Enterprise (custom — SSO, private cloud, audit log). Founding Member lifetime deal available: $99 one-time for permanent Team access. Pricing kicks in after beta. ## Key concepts - **Design** — the act of describing and structuring AI agents: naming roles, assigning tools, defining reporting lines, and setting access rules. Input is natural language; output is a structured JSON spec. - **Spec / team definition** — the structured JSON output of a design session. Follows the open Envelope schema. Readable by engineers, storable in Git, directly implementable. - **Agent role** — a named function in the team (e.g. "Lead Researcher", "Triage Agent") with a defined scope, tool access, model preference, and reporting relationship. - **Tool** — a connected service or API an agent can use (HubSpot, Slack, GitHub, Stripe, and 500+ more). Tool assignments are declared in the design, credentials are provided at implementation time. - **Reporting line** — the hierarchical relationship between agents in the team. Defines who delegates to whom and how outputs flow through the pipeline. - **Access policy** — per-agent outbound HTTP access controls. Declared in the design; enforced at runtime by the implementing platform. - **Human gate** — a checkpoint where a human must review or approve before the pipeline continues. Declared in the design at key decision points. - **Version** — designs are versioned. Each published version is immutable; editors work on drafts. Existing implementations keep running until upgraded. - **Export** — the design is exported as a JSON file following the open Envelope schema. This is the handoff artifact for IT teams. - **Handoff** — the process of passing the exported spec to an IT or engineering team for implementation on their chosen runtime. ## Open schema The Envelope schema is an open specification (Apache 2.0). Any platform can implement a conforming runtime. The schema `$id` is `https://schema.openenvelope.org/team/v1.json`. Designers don't need to know the schema — Envelope produces it automatically on export from the natural-language design session. - [Schema reference](https://openenvelope.org/docs/schema) — [Markdown](https://openenvelope.org/docs/schema.md): Full field-by-field reference for the `envelope-team` JSON schema — all fields, types, constraints, and examples. - [Schema versioning policy](https://openenvelope.org/docs/schema/versioning-policy) — [Markdown](https://openenvelope.org/docs/schema/versioning-policy.md): How the schema evolves, what counts as a breaking change, version lifecycle. ## Agent integration - [Envelope Skill](https://openenvelope.org/SKILL.md): Operating manual for AI agents — when to use Envelope, how to authenticate, the discover → generate → confirm → save workflow, gate handling, and rules (confirm before writing, never handle secrets, discover before creating). - [MCP server](https://openenvelope.org/docs/mcp) — [Markdown](https://openenvelope.org/docs/mcp.md): Connect to Envelope tools through MCP at `https://mcp.openenvelope.org/api/mcp`. Covers all 16 tools: list installs, run team, continue/reject gates, generate team, create team, update team, install, model routing, and more. - [Claude Code plugin](https://openenvelope.org/docs/claude-code) — [Markdown](https://openenvelope.org/docs/claude-code.md): Install the Envelope skill in Claude Code — teaches Claude to generate valid `.envelope.json` team definitions from plain-English descriptions. ## MCP & Claude Code Envelope runs a hosted MCP server at `https://mcp.openenvelope.org/api/mcp`. Connect it to Claude.ai or ChatGPT to work with your designs from any conversation. - [Connect to Claude.ai](https://openenvelope.org/guides/claude-ai) — [Markdown](https://openenvelope.org/guides/claude-ai.md): Add Envelope as a custom connector in Claude.ai — browse designs, export specs, and manage your team library from Claude conversations. - [Connect to ChatGPT](https://openenvelope.org/guides/chatgpt) — [Markdown](https://openenvelope.org/guides/chatgpt.md): Add Envelope as an app in ChatGPT via OAuth. Requires ChatGPT Plus, Team, or Enterprise. - [MCP Reference](https://openenvelope.org/mcp) — [Markdown](https://openenvelope.org/mcp.md): Interactive reference for all MCP tools — live curl examples, auth setup, error codes. - [Claude Code plugin](https://openenvelope.org/claude-code): Install the Envelope skill in Claude Code — teaches Claude to generate valid `.envelope.json` team definitions from plain-English descriptions. - [MCP documentation](https://openenvelope.org/docs/mcp) — [Markdown](https://openenvelope.org/docs/mcp.md): Full MCP server docs — tool list, auth, install instructions for Claude.ai and ChatGPT. - [Claude Code documentation](https://openenvelope.org/docs/claude-code) — [Markdown](https://openenvelope.org/docs/claude-code.md): Docs for the Claude Code plugin — what it does, how to install, usage examples. ## Blog - [From ops tool to design tool: why we pivoted](https://openenvelope.org/blog/design-tool-pivot) — [Markdown](https://openenvelope.org/blog/design-tool-pivot.md): The story of Envelope's pivot from an AI ops platform to a design tool — why the design-first framing unlocks a bigger market, and what the product looks like now. - [How agencies are productizing AI in 2026](https://openenvelope.org/blog/agencies-productizing-ai) — [Markdown](https://openenvelope.org/blog/agencies-productizing-ai.md): Practical guide for agencies packaging AI agent workflows as named monthly retainer deliverables. Covers the leverage play, delivery problem, and how Envelope solves it with reusable design templates. - [Run your Envelope teams from Claude and ChatGPT](https://openenvelope.org/blog/mcp-install) — [Markdown](https://openenvelope.org/blog/mcp-install.md): MCP server launch post — install steps for both clients, what each tool does, and the Claude Code skill. - [Schema launch](https://openenvelope.org/blog/schema-launch) — [Markdown](https://openenvelope.org/blog/schema-launch.md): The launch of the open Envelope schema — the open standard for agent definitions. ## Documentation - [Schema specification](https://openenvelope.org/docs/schema) — [Markdown](https://openenvelope.org/docs/schema.md): Full reference for the `envelope-team` JSON schema — all fields, types, constraints, and examples. Includes AgentDefinition, AccessPolicy, HumanGate, Schedule, and webhook event types. - [Ecosystem overview](https://openenvelope.org/docs/ecosystem) — [Markdown](https://openenvelope.org/docs/ecosystem.md): The builder/deployer model, NPM packages, and CLI tooling for engineers implementing Envelope specs. - [Platform integrations](https://openenvelope.org/docs/platforms) — [Markdown](https://openenvelope.org/docs/platforms.md): Supported runtimes for implementing an Envelope spec — Paperclip, Amazon Bedrock, Relevance AI, Envelope Managed, CrewAI, LangGraph, Vertex AI, Azure AI Foundry. - [Versioning](https://openenvelope.org/docs/versioning) — [Markdown](https://openenvelope.org/docs/versioning.md): How design versioning works — creating drafts, publishing without disrupting live implementations, rolling back. - [Access policy](https://openenvelope.org/docs/access-policy) — [Markdown](https://openenvelope.org/docs/access-policy.md): Per-agent network access controls — allowlist/denylist rules by hostname, method, and path prefix. - [Security & data flow](https://openenvelope.org/docs/security) — [Markdown](https://openenvelope.org/docs/security.md): What data reaches Envelope and what stays on your infrastructure. ## Guides - [Guides overview](https://openenvelope.org/guides): Index of all setup and how-to guides. - [Connect Claude.ai](https://openenvelope.org/guides/claude-ai) — [Markdown](https://openenvelope.org/guides/claude-ai.md): Add Envelope as a custom connector in Claude.ai — browse designs, export specs, and manage your team library from any conversation. - [Connect ChatGPT](https://openenvelope.org/guides/chatgpt) — [Markdown](https://openenvelope.org/guides/chatgpt.md): Add Envelope as an app in ChatGPT via OAuth. Requires ChatGPT Plus, Team, or Enterprise. - [Reading a spec](https://openenvelope.org/guides/reading-a-spec): How to read and interpret an exported agent spec — fields, agent structure, and handoff logic. - [Deploying from a spec](https://openenvelope.org/guides/deploying-from-spec) — [Markdown](https://openenvelope.org/guides/deploying-from-spec.md): How to hand off an exported spec to an engineering team or runtime for implementation. - [Git storage](https://openenvelope.org/guides/git-storage) — [Markdown](https://openenvelope.org/guides/git-storage.md): How to connect a GitHub repository so designs are stored and versioned there. - [Tool credentials](https://openenvelope.org/guides/tool-credentials) — [Markdown](https://openenvelope.org/guides/tool-credentials.md): How to add credentials for connected tools (HubSpot, Slack, GitHub, etc.) so agents can access them at runtime. ## Team library [AI agent library](https://openenvelope.org/library) — [Markdown](https://openenvelope.org/library.md): Browse public AI agent designs built on Envelope. Fork any team into your workspace and adapt it to your stack — free to start. ## Writing Envelope publishes practical guides and essays on multi-agent design, AI workflow automation, and the case for open standards. - [The anatomy of a multi-agent](https://openenvelope.org/writing/anatomy-multi-agent) — [Markdown](https://openenvelope.org/writing/anatomy-multi-agent.md): What a multi-agent actually is — sub-agents, model routing, ordered vs. concurrent pipelines, human gates, and the design step that makes it all work. Foundational reference. - [The stitching problem](https://openenvelope.org/writing/stitching-problem) — [Markdown](https://openenvelope.org/writing/stitching-problem.md): Why most multi-agent systems fail at the connections between agents, not inside them — and why the fix is a design decision, not a better model or smarter prompt. - [What is AI workflow automation?](https://openenvelope.org/writing/ai-workflow-automation) — [Markdown](https://openenvelope.org/writing/ai-workflow-automation.md): How AI workflow automation differs from traditional automation (Make, Zapier, n8n), why AI agents change the model, and what good multi-agent workflow design looks like. - [How to design an AI workflow before you build it](https://openenvelope.org/writing/design-ai-workflow) — [Markdown](https://openenvelope.org/writing/design-ai-workflow.md): Step-by-step process for designing a multi-agent workflow from objective to spec — agents, roles, tools, handoffs, pipeline structure, gates, and model assignments — before writing any code. - [Model routing in multi-agent workflows](https://openenvelope.org/writing/model-routing) — [Markdown](https://openenvelope.org/writing/model-routing.md): Why different agents in the same system should run on different AI models, how to match each role to the right model, and what model routing looks like in a worked example. - [AI agents need managers too](https://openenvelope.org/writing/ai-agents-need-managers) — [Markdown](https://openenvelope.org/writing/ai-agents-need-managers.md): Why governance is the infrastructure that makes AI agent delegation safe — defined scope, role-based access, audit trail, human gates. - [The model path won't solve coordination](https://openenvelope.org/writing/model-path-governance) — [Markdown](https://openenvelope.org/writing/model-path-governance.md): Better models won't solve the coordination problem. The execution layer is the governance layer. - [Why open standards matter for AI infrastructure](https://openenvelope.org/writing/open-standards-ai-infrastructure) — [Markdown](https://openenvelope.org/writing/open-standards-ai-infrastructure.md): The case for an open definition format for AI agents — portability, validators, registries. - [The platform trap in AI](https://openenvelope.org/writing/platform-trap-in-ai) — [Markdown](https://openenvelope.org/writing/platform-trap-in-ai.md): Choosing an orchestration platform is a format choice. Closed formats create lock-in denser than normal infra. - [Credentials, trust and the AI operator problem](https://openenvelope.org/writing/credentials-trust-operator-problem) — [Markdown](https://openenvelope.org/writing/credentials-trust-operator-problem.md): The three-party credential structure, access policy as enforcement, human gates for irreversible actions. - [Human in the loop and the autonomous agent problem](https://openenvelope.org/writing/hitl-autonomous-agent-problem) — [Markdown](https://openenvelope.org/writing/hitl-autonomous-agent-problem.md): Why keeping humans in the loop matters even as agents grow more capable. - [What makes a good agent role definition](https://openenvelope.org/writing/agent-role-definition) — [Markdown](https://openenvelope.org/writing/agent-role-definition.md): Roles vs prompts, agent scope and hierarchy, capabilities as constraints. - [The composable AI thesis](https://openenvelope.org/writing/composable-ai-thesis) — [Markdown](https://openenvelope.org/writing/composable-ai-thesis.md): Why composable, narrow multi-agent teams outperform monolithic agents. - [Narrow by design](https://openenvelope.org/writing/narrow-by-design) — [Markdown](https://openenvelope.org/writing/narrow-by-design.md): The argument for building multi-agent teams from narrow, specialised agents. ## Community [Envelope Community](https://openenvelope.org/community): The Envelope Discord — where designers, PMs, and engineers discuss AI agent design, share what they've built, and get help. Channels include #schema-discussion, #design-help, #showcase, and #platform-integrations. ## Templates by tool Envelope has dedicated pages for every supported integration, listing community designs that use that tool. Append `.md` to any tool URL for a clean plain-text version (e.g. https://openenvelope.org/tools/hubspot.md). - [HubSpot AI agents](https://openenvelope.org/tools/hubspot) — [Markdown](https://openenvelope.org/tools/hubspot.md) - [Slack AI agents](https://openenvelope.org/tools/slack) — [Markdown](https://openenvelope.org/tools/slack.md) - [Zendesk AI agents](https://openenvelope.org/tools/zendesk) — [Markdown](https://openenvelope.org/tools/zendesk.md) - [Salesforce AI agents](https://openenvelope.org/tools/salesforce) — [Markdown](https://openenvelope.org/tools/salesforce.md) - [GitHub AI agents](https://openenvelope.org/tools/github) — [Markdown](https://openenvelope.org/tools/github.md) - [Linear AI agents](https://openenvelope.org/tools/linear) — [Markdown](https://openenvelope.org/tools/linear.md) - [Stripe AI agents](https://openenvelope.org/tools/stripe) — [Markdown](https://openenvelope.org/tools/stripe.md) - [Notion AI agents](https://openenvelope.org/tools/notion) — [Markdown](https://openenvelope.org/tools/notion.md) - [Jira AI agents](https://openenvelope.org/tools/jira) — [Markdown](https://openenvelope.org/tools/jira.md) - [Gmail AI agents](https://openenvelope.org/tools/gmail) — [Markdown](https://openenvelope.org/tools/gmail.md) - [Intercom AI agents](https://openenvelope.org/tools/intercom) — [Markdown](https://openenvelope.org/tools/intercom.md) - [Freshdesk AI agents](https://openenvelope.org/tools/freshdesk) — [Markdown](https://openenvelope.org/tools/freshdesk.md) - [Airtable AI agents](https://openenvelope.org/tools/airtable) — [Markdown](https://openenvelope.org/tools/airtable.md) - [Asana AI agents](https://openenvelope.org/tools/asana) — [Markdown](https://openenvelope.org/tools/asana.md) - [Pipedrive AI agents](https://openenvelope.org/tools/pipedrive) — [Markdown](https://openenvelope.org/tools/pipedrive.md) - [Discord AI agents](https://openenvelope.org/tools/discord) — [Markdown](https://openenvelope.org/tools/discord.md) - [Twitter/X AI agents](https://openenvelope.org/tools/twitter) — [Markdown](https://openenvelope.org/tools/twitter.md) - [Shopify AI agents](https://openenvelope.org/tools/shopify) — [Markdown](https://openenvelope.org/tools/shopify.md) - [Twilio AI agents](https://openenvelope.org/tools/twilio) — [Markdown](https://openenvelope.org/tools/twilio.md) - [ClickUp AI agents](https://openenvelope.org/tools/clickup) — [Markdown](https://openenvelope.org/tools/clickup.md) - [Monday AI agents](https://openenvelope.org/tools/monday) — [Markdown](https://openenvelope.org/tools/monday.md) - [Microsoft AI agents](https://openenvelope.org/tools/microsoft) — [Markdown](https://openenvelope.org/tools/microsoft.md) - [SendGrid AI agents](https://openenvelope.org/tools/sendgrid) — [Markdown](https://openenvelope.org/tools/sendgrid.md) ## Role landing pages Envelope has pages for common agent roles in AI agent designs. Append `.md` to any role URL for a clean plain-text version (e.g. https://openenvelope.org/roles/sales.md). - [Sales roles](https://openenvelope.org/roles/sales) — [Markdown](https://openenvelope.org/roles/sales.md) - [Support roles](https://openenvelope.org/roles/support) — [Markdown](https://openenvelope.org/roles/support.md) - [Engineering roles](https://openenvelope.org/roles/engineering) — [Markdown](https://openenvelope.org/roles/engineering.md) - [Marketing roles](https://openenvelope.org/roles/marketing) — [Markdown](https://openenvelope.org/roles/marketing.md) - [Operations roles](https://openenvelope.org/roles/operations) — [Markdown](https://openenvelope.org/roles/operations.md) - [Finance roles](https://openenvelope.org/roles/finance) — [Markdown](https://openenvelope.org/roles/finance.md) - [HR roles](https://openenvelope.org/roles/hr) — [Markdown](https://openenvelope.org/roles/hr.md)