Zero vs AgentMail

Portability

1. switcherMy mail stays reachable over open protocols and standard formats — IMAP/JMAP/SMTP access and standards-based export — so no client can lock me in

   weight 2 · round to AgentMail
   Zero—none0/10

   Evidence shows Zero connects to providers like Gmail/Outlook and offers self-hosting and an MCP server for AI actions, but nothing in the pack mentions IMAP/JMAP/SMTP protocol access or standards-based mail export for portability — the core of this switcher story is unaddressed.

   • [github] “Unified Inbox – Connect multiple email providers like Gmail, Outlook, and more.”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [github] “Self-Hosting Freedom – Run your own email app with ease.”
   • [claimed-docs] “Self-hosting capabilities”

   proof ↗⚑ flag

   AgentMail~partialclaimed6/10

   AgentMail documents IMAP/SMTP compatibility, letting any standard mail client (Outlook, Thunderbird, Apple Mail) connect to an AgentMail inbox, which supports the open-protocol reachability part of the story. However, there is no mention of JMAP support or of a standards-based export/data-portability mechanism for migrating mail elsewhere. Missing for 10: JMAP protocol support, documented mailbox/data export or migration tooling, and independent confirmation that IMAP/SMTP access works reliably in practice.

   • [claimed-docs] “Connect Outlook, Thunderbird, Apple Mail, or any IMAP/SMTP-compatible client to your AgentMail inbox”

   proof ↗⚑ flag

2. switcherSelf-host the email app and keep the mail pipeline under my own control

   weight 1 · round to Zero
   Zero✓fullprobed7/10

   Zero is explicitly open-source and self-hostable, with GitHub docs stating 'Self-Hosting Freedom – Run your own email app with ease' and a probe confirming a real, keyless-cloneable source tree with docker-compose files for self-hosting the full mail pipeline (DB, prod services). This gives a switcher genuine control over their own instance rather than relying on a hosted SaaS. Missing for 10: detailed self-hosting setup/migration docs (e.g. IMAP/SMTP backend specifics), independent hands-on reports of a completed self-hosted deployment, and confirmation of full mailbox portability beyond Gmail/Outlook OAuth integration.

   • [github] “Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “⚙️ Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “gives users the power to **self-host** their own email app”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”
   • [claimed-docs] “Self-hosting capabilities”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail is documented as a hosted email API/service (custom domains, hosted MCP server, webhooks) with no mention anywhere of a self-hosted deployment option; a competitor's marketing even highlights itself as the 'self-hosted drop-in replacement' for AgentMail, implying AgentMail itself is cloud-only.

   • [claimed-docs] “using your own custom domains is essential for production applications. It gives you control over your sending reputation, which is the sing…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [community] “agentmail charges $20/mo for 10 inboxes. autopilot gives you unlimited inboxes for the cost of a postgres row, positioning itself as a self-…”

   proof ↗⚑ flag

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to AgentMail
   Zero~partialprobed6/10

   The repo ships an AGENT.md (agent-configuration doc) and a detailed MCP.md describing the MCP server's tool surface, both of which are exactly the kind of machine/agent-oriented documentation an AI agent could be pointed at; this was confirmed by a hands-on probe of the actual repo tree. However there is no evidence of a dedicated llms.txt file or any explicit guidance framing these docs as an 'agent-readable spec' in the llms.txt convention. Missing for 10: an actual llms.txt file, first-party statement that docs are structured for LLM consumption, and independent confirmation an agent successfully parsed these docs.

   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”
   • [probe] “official MCP server documented at https://github.com/Mail-0/Zero/blob/staging/MCP.md”
   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”

   proof ↗⚑ flag

   AgentMail✓fullprobed9/10

   AgentMail hosts a live llms.txt file (verified HTTP 200) with a clear agent-oriented summary of its docs, and its entire documentation set is written in agent-consumable .md format (e.g., quickstart.md, messages.md) alongside an OpenAPI spec, MCP server, and CLI docs, making it easy for an agent to be pointed at and consume its docs. Missing for 10: no independent/community confirmation of an agent successfully navigating llms.txt end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.agentmail.to/llms.txt # AgentMail | Documentation > AgentMail is an email API built for AI agents.…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “The agent registers itself using the human email you provide and gets back an API key, inbox ID, and organization ID.”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to AgentMail
   Zero—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   AgentMail✓fullprobed7/10

   AgentMail is fundamentally API/SDK-driven ('Create, manage, and operate email inboxes entirely via API'), with a documented OpenAPI spec, official CLI, and webhook/websocket event delivery that support scripted, non-interactive automation pipelines. No explicit CI/CD example or pipeline walkthrough is given, so full CI-specific validation is inferred rather than directly documented. Missing for 10: an explicit CI/CD pipeline example or GitHub Actions integration, and independent confirmation of headless use in production automation.

   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”

   proof ↗⚑ flag

3. ai-native userConnect an agent via an official MCP server

   weight 3 · round drawn
   Zero✓fullprobed8/10

   Zero ships a documented, named 'Zero MCP' server (MCP.md) exposing concrete tools (email CRUD, labels, AI compose, mailbox Q&A, web search) with an authentication method (Better Auth session token, OAuth coming soon), confirmed by an independent runtime probe finding the file in the actual repo. Missing for 10: independent hands-on verification that a third-party agent successfully connects and uses the server end-to-end, and OAuth is still unimplemented.

   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [probe] “official MCP server documented at https://github.com/Mail-0/Zero/blob/staging/MCP.md”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail✓fullprobed8/10

   AgentMail is a service/API product (not itself an agent), so the MCP-server axis applies, and docs confirm a hosted official MCP server at https://mcp.agentmail.to/mcp exposing inbox, message, thread, draft, and attachment tools to any compatible client, corroborated by a probe hit. Missing for 10: independent/hands-on confirmation that the MCP server works reliably in practice beyond first-party docs.

   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at `https://mcp.agentmail.to/mcp` that exposes inbox, message, thread, draft, and attachment tools to any…”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to AgentMail
   Zero—none0/10

   Zero's evidence shows an MCP server (ZeroMCP) and self-hosting via docker-compose, plus a pnpm-based dev script for Drizzle Studio, but no official CLI tool for AI-native interaction with the product itself is documented anywhere in the pack.

   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [claimed-docs] “View and edit data with Drizzle Studio pnpm db:studio”
   • [probe] “official MCP server documented at https://github.com/Mail-0/Zero/blob/staging/MCP.md”

   proof ↗⚑ flag

   AgentMail✓fullprobed7/10

   AgentMail documents an official CLI (docs.agentmail.to/integrations/cli) that lets users create inboxes, send messages, and manage threads without writing code, corroborated by a probe confirming the page exists. Missing for 10: no independent/community hands-on confirmation of CLI usage or installation details beyond the docs themselves.

   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to AgentMail
   Zero✓fullprobed8/10

   Zero ships a documented MCP server (ZeroMCP) exposing a public, structured API for emails, labels, AI compose, mailbox Q&A, and web search, with authentication documented via Better Auth session tokens (OAuth coming soon), corroborated by a runtime probe confirming the real MCP.md and AGENT.md files in the repo. missing for 10: independent third-party usage/testing of the MCP API beyond first-party docs and a single runtime probe, and full OAuth support (currently listed as coming soon).

   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [probe] “official MCP server documented at https://github.com/Mail-0/Zero/blob/staging/MCP.md”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail✓fullprobed9/10

   AgentMail is explicitly an API-first product: docs describe registering agents via API, creating inboxes, sending/searching messages, webhooks, permissions, etc., and a live OpenAPI spec is confirmed at docs.agentmail.to/openapi.json. This gives strong first-party and probe-verified evidence of a documented, comprehensive public API. Missing for 10: independent third-party hands-on validation of the API itself (community feedback focuses on website/pricing, not API usage).

   • [claimed-docs] “The agent registers itself using the human email you provide and gets back an API key, inbox ID, and organization ID.”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.agentmail.to/llms.txt # AgentMail | Documentation > AgentMail is an email API built for AI agents.…”
   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to AgentMail
   Zero—none0/10

   Zero's MCP server documents authentication via a Better Auth session token (or future OAuth), but there is no evidence of scoped or least-privilege credential issuance, permission granularity, or agent-specific token scoping — auth appears to be a single session-level token granting full account access. Missing for 10: any documentation of scopes/permissions models, per-agent credential minting, or restricted-access tokens for agents.

   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail✓fullclaimed8/10

   Docs explicitly describe scoped API keys restricted to a single pod or inbox, per-customer pods with scoped keys for multi-tenancy, and a dedicated Permissions feature to restrict what an API key can do — directly matching the least-privilege credential story. Missing for 10: independent/hands-on verification that scoping actually enforces restrictions in practice, and detail on granularity of permission types beyond pod/inbox scope.

   • [claimed-docs] “create a Pod per customer, give them a scoped API key, and route webhook events to the right place.”
   • [claimed-docs] “Scoped API keys restrict access to a single pod or a single inbox.”
   • [claimed-docs] “`Permissions` let you restrict what an API key can do.”
   • [claimed-docs] “Create one pod per customer/tenant in your system”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to AgentMail
   Zero~partialprobed5/10

   Zero doesn't publish a traditional language SDK, but it does document an official 'ZeroMCP' server (MCP.md) with concrete tool endpoints (email CRUD, labels, AI compose, mailbox Q&A) plus AGENT.md agent-configuration docs, giving AI-native developers a documented, official programmatic interface to build against, corroborated by a runtime probe confirming these files exist in the live repo. Missing for 10: an actual client SDK/library (Python/JS package), auth beyond a session token (OAuth marked 'coming soon'), and independent third-party developer usage reports.

   • [claimed-docs] “Modify email labels”
   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [probe] “official MCP server documented at https://github.com/Mail-0/Zero/blob/staging/MCP.md”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”
   • [github] “🚀 Developer-Friendly – Built with extensibility and integrations in mind.”

   proof ↗⚑ flag

   AgentMail✓fullprobed8/10

   AgentMail is fundamentally an API-first product with dedicated docs, OpenAPI spec, quickstart showing API key/SDK registration, and popovers showing SDK examples praised by a community reviewer, confirming real SDK-based building. Missing for 10: explicit list of language-specific SDKs (e.g. Python/TS/Go) and independent third-party developer testimonials beyond the dashboard praise.

   • [claimed-docs] “The agent registers itself using the human email you provide and gets back an API key, inbox ID, and organization ID.”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [community] “What I am most impressed by is the popovers in your dashboard, which show SDK examples. This is a brilliant UI idea (executed with great pol…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to AgentMail
   Zero—none0/10

   Evidence covers Zero's MCP server (tool-calling actions like search, compose, label management) but nowhere mentions webhooks, event subscriptions, or push notifications for external systems to react to inbox events.

   ⚑ flag

   AgentMail✓fullclaimed9/10

   AgentMail's docs explicitly support webhook subscriptions: registering a URL to receive POST requests on email events instead of polling, avoiding the need for constant API checks. This is a first-party documented, core feature directly matching the story. Missing for 10: independent/hands-on confirmation that webhooks work reliably in practice.

   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”

   proof ↗⚑ flag

Agentic features

1. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to AgentMail
   Zero—none0/10

   Evidence shows an MCP server exposing on-demand email tools (search, compose, label, delete) that an AI client can call interactively, but nothing shows Zero itself scheduling or running autonomous background automations/triggers/workflows without a user or agent actively invoking them.

   ⚑ flag

   AgentMail~partialclaimed5/10

   AgentMail provides the building blocks for background automation—webhooks and persistent WebSocket connections that push email events in real time instead of requiring polling—so an agent can react autonomously to inbound mail without a human in the loop. However, AgentMail itself is just email infrastructure; there's no evidence of a built-in scheduler, workflow engine, or persistent agent runtime that executes autonomous logic—that has to be built by the user on top of the webhook/websocket feed. Missing for 10: evidence of a native scheduling/automation engine, documented autonomous background job execution, or independent confirmation that these mechanisms reliably drive unattended agent workflows.

   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”
   • [claimed-docs] “WebSockets provide a persistent, bidirectional connection to AgentMail for receiving email events in real-time.”
   • [claimed-docs] “WebSockets don't require a public URL or external tools like ngrok.”

   proof ↗⚑ flag

2. ai-native userOperate the product with natural-language commands

   weight 2 · round to Zero
   Zero✓fullcommunity7/10

   Zero's founder describes it as an AI-powered email client where users can chat with their inbox, ask questions about threads, and have AI draft replies, and the MCP docs confirm natural-language driven actions (compose, search, ask questions, web search) — this directly matches AI-native NL command operation. Missing for 10: independent hands-on verification of the actual chat UI/NL command interface beyond founder claims and MCP protocol docs.

   • [community] “Zero founder describes it as an AI-powered email client that auto-categorizes, summarizes threads, drafts replies, and lets users chat with …”
   • [claimed-docs] “Ask questions about specific email threads”
   • [claimed-docs] “Ask questions about mailbox content - Ask questions about specific email threads”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [claimed-docs] “Compose emails with AI assistance”

   proof ↗⚑ flag

   AgentMail~partialprobed6/10

   AgentMail exposes a hosted MCP server with inbox/message/thread/draft tools that lets any MCP-compatible AI agent operate the product via natural language, and also ships a CLI for no-code operations. However, there's no first-party chat/NL interface of its own, nor independent evidence of successful natural-language operation in practice. Missing for 10: hands-on demonstration of natural-language command execution, a dedicated conversational UI beyond MCP tool-calling.

   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at `https://mcp.agentmail.to/mcp` that exposes inbox, message, thread, draft, and attachment tools to any…”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to AgentMail
   Zero—none0/10

   Zero is an email client with an MCP server and docs (MCP.md, ROADMAP.md), but there is no evidence of an interactive API reference (e.g., Swagger/OpenAPI explorer, Postman collection, or runnable code sandbox) for AI-native users to explore and execute example calls.

   ⚑ flag

   AgentMail~partialprobed5/10

   AgentMail exposes a machine-readable OpenAPI spec (agentmail-probe-2) and its docs site includes language-switchable code snippets (Python/curl) plus SDK example popovers praised by users (agentmail-comm-2, agentmail-comm-7), suggesting an interactive reference. However, there is no evidence of a true 'try it now' runnable/executable API console, and independent reports note the docs site itself is slow and glitchy (agentmail-comm-1, agentmail-comm-3), undermining a smooth interactive experience. Missing for 10: confirmation of an actual runnable/sandboxed request execution feature, and resolution of the reported performance/UX issues on the docs site.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [community] “The website is really bad. Moving from Python to curl tab on the site shows noticeable lag - I have seen 2-3 whole websites load faster in t…”
   • [community] “What I am most impressed by is the popovers in your dashboard, which show SDK examples. This is a brilliant UI idea (executed with great pol…”
   • [community] “"Application error: a client-side exception has occurred while loading www.agentmail.to"... Failed to create WebGL context... Cookie rejecte…”
   • [community] “I have written about how slow the website is... the amount of lag is something I have genuinely never witnessed in any website... I can't vi…”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to AgentMail
   Zero—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   AgentMail✓fullprobed9/10

   A probe confirms the OpenAPI spec is live and machine-readable at https://docs.agentmail.to/openapi.json (HTTP 200, contains "openapi" key), backed by documented API-first design. Missing for 10: no independent third-party corroboration of spec completeness or SDK auto-generation from it.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Zero—none0/10

   Zero is an AI email client whose evidence covers MCP tools for real mailbox operations (send/delete/label emails) and self-hosting, but nothing describes a sandbox, test/staging mode, or mock data environment isolated from production email accounts.

   ⚑ flag

   AgentMail—none0/10

   No evidence of a dedicated sandbox/test environment separate from production; the docs describe creating inboxes on-demand, but nothing indicates an isolated test mode that avoids touching real production data or sending real emails.

   ⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Zero—none0/10

   Evidence describes Zero's MCP server capabilities and self-hosting, but no documentation anywhere mentions API versioning, version numbers, or a deprecation policy for its MCP/API surface. missing for 10: any mention of API versioning scheme, changelog/deprecation policy, or backward-compatibility guarantees.

   ⚑ flag

   AgentMail—none0/10

   Evidence shows an OpenAPI spec and general API docs, but there is no mention anywhere of API versioning scheme or a documented deprecation policy for endpoints.

   ⚑ flag

Agent workflows

1. ai-native userAn external agent — Claude, ChatGPT, or my own — can read, triage, draft, and send my email end to end through a documented connection

   weight 2 · round drawn
   Zero✓fullprobed8/10

   Zero documents an official MCP server (MCP.md, verified by probe) enabling agents like Claude to read threads, ask questions about mailbox content, compose with AI assistance, and create/send drafts and new emails, plus manage labels — covering triage, drafting, and sending end to end via Better Auth session token auth. missing for 10: no hands-on third-party report of an external agent (Claude/ChatGPT) actually completing a full read-triage-send workflow, and OAuth support is still 'coming soon' rather than shipped.

   • [claimed-docs] “Compose emails with AI assistance”
   • [claimed-docs] “Ask questions about specific email threads”
   • [claimed-docs] “Ask questions about mailbox content - Ask questions about specific email threads”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [claimed-docs] “You can connecto ZeroMCP using two methods: 1. Better Auth session token 2. OAuth (Coming soon)”
   • [probe] “official MCP server documented at https://github.com/Mail-0/Zero/blob/staging/MCP.md”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail✓fullprobed8/10

   AgentMail documents a hosted MCP server exposing inbox, message, thread, draft, and attachment tools, plus a full API/CLI for creating inboxes, reading/searching threads, drafting (with human-in-the-loop review), and sending messages with attachments — enabling any MCP-compatible agent (Claude, ChatGPT, custom) to triage and send email end to end. missing for 10: independent hands-on verification of an external agent completing a full read-triage-send workflow via the MCP connection (only vendor docs and probes confirm the endpoint, no third-party usage report).

   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at `https://mcp.agentmail.to/mcp` that exposes inbox, message, thread, draft, and attachment tools to any…”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”
   • [claimed-docs] “Human-in-the-Loop Review: An agent can create a `Draft` for a sensitive or important `Message`, which a human can then review and approve be…”
   • [claimed-docs] “To start a new conversation, you can send a Message from one of your inboxes.”
   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”
   • [claimed-docs] “Your agents can both send `Attachments` in outgoing `Messages` and process `Attachments` from incoming `Messages`.”
   • [claimed-docs] “You can cc or bcc a real person on any message your agent sends, creating a "human-in-the-loop" workflow for oversight, escalations, or qual…”

   proof ↗⚑ flag

Ai assistant

1. ai-native userAsk an assistant questions across my whole inbox and calendar — who said what, what's outstanding — and get grounded answers

   weight 2 · round to Zero
   Zero~partialprobed6/10

   Zero's MCP server explicitly supports asking questions about mailbox content and specific email threads, plus AI compose, search, and labels, and community commentary confirms an AI-powered 'chat with your inbox' experience. However, evidence doesn't show cross-inbox/whole-calendar synthesis, calendar integration, or 'who said what / what's outstanding' style grounded multi-thread reasoning — the documented Q&A appears scoped to mailbox/thread level rather than full inbox+calendar grounding. missing for 10: calendar integration/awareness, evidence of synthesizing across the entire inbox (not just single threads), independent hands-on verification of grounded multi-source answers.

   • [claimed-docs] “Ask questions about specific email threads”
   • [claimed-docs] “Ask questions about mailbox content - Ask questions about specific email threads”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [community] “Zero founder describes it as an AI-powered email client that auto-categorizes, summarizes threads, drafts replies, and lets users chat with …”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail is developer infrastructure (an email API/MCP server) for building agent-driven email workflows, not an end-user assistant that answers grounded questions across inbox and calendar. Evidence shows full-text search across threads and MCP tool exposure (docs-5, docs-12), but there is no calendar integration anywhere in the evidence, and no shipped assistant/chat interface that synthesizes 'who said what' or 'what's outstanding' answers for a user.

   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”
   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”

   proof ↗⚑ flag

Ai drafting

1. ai-native userAI drafts replies in my own voice and tone — ready to review and send, not generic boilerplate

   weight 3 · round to Zero
   Zero~partialcommunity5/10

   Zero's MCP docs and founder description confirm AI drafts replies ('Compose emails with AI assistance', 'drafts replies') as a core feature, but no evidence describes voice/tone personalization or learning the user's writing style. Missing for 10: documentation of voice/tone matching or personalization mechanism, and independent hands-on verification that drafts read as the user's own voice rather than generic AI text.

   • [claimed-docs] “Compose emails with AI assistance”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [community] “Zero founder describes it as an AI-powered email client that auto-categorizes, summarizes threads, drafts replies, and lets users chat with …”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail provides Draft objects and human-in-the-loop review (an agent can create a Draft for a human to approve before sending), but there is no evidence that AgentMail itself learns or applies the user's personal voice/tone when generating drafts — it is an email infrastructure/API for agents, not a personalization/writing-style engine.

   • [claimed-docs] “Human-in-the-Loop Review: An agent can create a `Draft` for a sensitive or important `Message`, which a human can then review and approve be…”
   • [claimed-docs] “You can cc or bcc a real person on any message your agent sends, creating a "human-in-the-loop" workflow for oversight, escalations, or qual…”

   proof ↗⚑ flag

Ai triage

1. ai-native userAI triages my inbox for me — auto-labeling, categorizing, and surfacing what needs attention — with behavior I can steer and audit

   weight 3 · round to Zero
   Zero~partialprobed6/10

   Community and docs evidence show Zero markets itself as an AI-powered inbox that auto-categorizes emails, and its MCP server exposes tools to modify/create labels, filter/search by label, and answer questions about threads/mailbox content, giving a steerable interface for AI actions. However, there's no explicit documentation of automatic prioritization/surfacing of 'what needs attention' or an audit log of AI triage decisions beyond the generic MCP action list. Missing for 10: dedicated 'needs attention' surfacing/prioritization feature, explicit audit trail or history of AI-taken triage actions, and independent hands-on verification of auto-labeling accuracy.

   • [community] “Zero founder describes it as an AI-powered email client that auto-categorizes, summarizes threads, drafts replies, and lets users chat with …”
   • [claimed-docs] “Modify email labels”
   • [claimed-docs] “Create new custom labels with custom colors”
   • [claimed-docs] “Search emails with custom queries - Filter emails by labels”
   • [claimed-docs] “Ask questions about mailbox content - Ask questions about specific email threads”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail provides developer primitives (Labels, Lists, full-text search, webhooks) that a developer could use to build inbox triage, but there is no evidence of AgentMail itself performing AI-driven auto-labeling, categorization, or surfacing-what-needs-attention out of the box — Labels are described as manually tracked conversation states, not an automated triage engine, and no docs describe a built-in AI classifier or steerable/auditable triage policy.

   • [claimed-docs] “Use `Labels` to track the state of a conversation.”
   • [claimed-docs] “`Lists` allow you to filter emails by allowing or blocking specific email addresses or domains.”
   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”
   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Zero
   Zero~partialprobed5/10

   Zero's MCP server exposes email actions like 'Bulk delete emails' and 'Bulk archive emails' explicitly labeled as bulk operations, plus label/search operations that could apply across many items. However, evidence does not specify limits, batch size, or confirm bulk semantics beyond these two named actions, nor is there hands-on confirmation of bulk behavior at scale. missing for 10: independent/hands-on verification of bulk operations at scale, documentation of batch limits or performance, evidence of bulk operations beyond delete/archive (e.g., bulk label/move/send).

   • [claimed-docs] “Bulk delete emails - Bulk archive emails”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail~partialclaimed4/10

   Docs confirm the platform is fully API-driven and explicitly supports creating 'tens, hundreds, or even thousands' of inboxes on demand, implying agents can script bulk creation, but there's no documented dedicated bulk/batch endpoint for messages, threads, or other items (e.g., bulk send, bulk label, bulk delete). Missing for 10: dedicated batch/bulk API endpoints for messages/threads, documented rate-limit or batching guidance, hands-on evidence of bulk operations at scale.

   • [claimed-docs] “You can create tens, hundreds, or even thousands of Inboxes for your agents on demand.”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to AgentMail
   Zero—none0/10

   Evidence shows Zero as an AI email client with MCP tool actions (search, compose, label, etc.) but no documented rule-based automation engine that triggers actions on events (e.g., 'when email arrives from X, do Y'). All actions appear to be user- or agent-invoked rather than event-triggered automation. Missing for full credit: any documented trigger/condition/action rules engine or scheduled/event-based automation feature.

   • [claimed-docs] “Modify email labels”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail~partialclaimed5/10

   AgentMail exposes event-driven infrastructure (webhooks and websockets) so external code can react to inbox events, and Lists provide simple automatic allow/block rules on senders/domains, but there's no built-in rule engine for defining conditional 'if X then do Y' automations inside the product itself — the actual rule logic must be implemented by the developer/agent consuming the webhook. missing for 10: a native rules/automation engine (e.g. conditional triggers on subject/content beyond allow-block lists), and independent confirmation that webhook-driven automation works reliably in production.

   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”
   • [claimed-docs] “WebSockets provide a persistent, bidirectional connection to AgentMail for receiving email events in real-time.”
   • [claimed-docs] “`Lists` allow you to filter emails by allowing or blocking specific email addresses or domains.”
   • [claimed-docs] “Use `Labels` to track the state of a conversation.”

   proof ↗⚑ flag

Sending

1. power-userSee whether and when recipients opened my email

   weight 1 · round drawn
   Zero—none0/10

   No evidence anywhere in the pack mentions read receipts, open tracking, or notifications about when recipients open emails; the MCP/docs only cover sending, drafting, labeling, and searching emails.

   ⚑ flag

   AgentMail—none0/10

   No evidence anywhere in the pack mentions read receipts, open tracking, or delivery/open status for sent messages; AgentMail's docs cover inboxes, threads, webhooks, drafts, labels, etc., but nothing about tracking whether a recipient opened an email.

   ⚑ flag

2. power-userSchedule an email to send later and undo a send within a grace window

   weight 2 · round drawn
   Zero—none0/10

   No evidence anywhere in the pack mentions scheduled send or undo-send functionality; MCP docs list send/draft/delete but nothing about delayed sending or a grace-window recall.

   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts”

   proof ↗⚑ flag

   AgentMail—none0/10

   No evidence anywhere in the pack of scheduled sending or an undo-send grace window; AgentMail's documented features cover inboxes, messages, drafts, threads, webhooks, and human-in-the-loop review, but nothing about delayed/scheduled send or send-cancellation.

   ⚑ flag

Templates

1. power-userInsert saved snippets or templates — with variables and attachments — instead of retyping the same reply

   weight 2 · round drawn
   Zero—none0/10

   No evidence pack item mentions saved snippets, canned responses, or templates with variables/attachments; the docs describe AI-assisted composing, MCP tools, labels, and self-hosting but nothing about a snippet/template insertion feature.

   ⚑ flag

   AgentMail—none0/10

   AgentMail is an API/infrastructure product for agent-driven email (inboxes, messages, drafts, attachments, webhooks) with no evidence of a saved snippets/templates library or variable-substitution feature for composing replies; nothing in the docs mentions reusable templates or canned responses.

   ⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to AgentMail
   Zero~partialprobed6/10

   Zero's MCP server exposes many core email actions (search, send, draft, delete, labels, AI compose, thread Q&A) that mirror UI functionality, giving strong API-parity for mail operations. However missing for 10: no evidence of API parity for UI-specific settings like customizable keyboard shortcuts, UI theming/customization, unified inbox provider management, or account/connection setup via API — these remain UI-only per docs, and there's no independent confirmation the MCP surface is fully comprehensive versus a curated subset.

   • [claimed-docs] “Compose emails with AI assistance”
   • [claimed-docs] “Ask questions about specific email threads”
   • [claimed-docs] “Search emails with custom queries - Filter emails by labels”
   • [claimed-docs] “Ask questions about mailbox content - Ask questions about specific email threads”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Get all user labels - Create new custom labels with custom colors - Delete existing labels”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”
   • [claimed-docs] “Customizable keyboard shortcuts”
   • [github] “Customizable UI & Features – Tailor your email experience the way you want it.”

   proof ↗⚑ flag

   AgentMail✓fullprobed8/10

   AgentMail is explicitly API-first ('Create, manage, and operate email inboxes entirely via API'), with a documented OpenAPI spec, CLI, and MCP server all built atop the same API surface (inboxes, messages, threads, drafts, webhooks, attachments, permissions, pods) — no UI-exclusive features are mentioned anywhere in the docs. missing for 10: an explicit statement or independent test confirming 1:1 parity between the dashboard UI and API (e.g., that every dashboard action maps to a documented endpoint).

   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”
   • [claimed-docs] “create a Pod per customer, give them a scoped API key, and route webhook events to the right place.”
   • [claimed-docs] “Scoped API keys restrict access to a single pod or a single inbox.”
   • [claimed-docs] “`Permissions` let you restrict what an API key can do.”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to AgentMail
   Zero—none0/10

   Evidence shows Zero is self-hostable, open-source, and doesn't sell user data, plus a Drizzle Studio DB viewer for self-hosters, but there is no documented data-export feature (e.g., mbox/EML export, takeout tool) letting a user extract all their mail data in an open format and leave the service.

   • [github] “gives users the power to **self-host** their own email app”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [github] “Zero does not track, collect, or sell your data in any way.”
   • [claimed-docs] “View and edit data with Drizzle Studio pnpm db:studio”

   proof ↗⚑ flag

   AgentMail~partialprobed5/10

   AgentMail supports connecting standard IMAP/SMTP clients (Outlook, Thunderbird, Apple Mail), which gives users open-protocol access to their mailbox data rather than lock-in to a proprietary format, and the OpenAPI spec/CLI allow programmatic retrieval of messages. However there is no explicit documented 'export all data' or account-portability/data-takeout feature, and no evidence of exporting threads/attachments in bulk open formats. Missing for 10: explicit bulk export/backup tooling, documented data-portability guarantees, and confirmation of full account deletion with data takeout.

   • [claimed-docs] “Connect Outlook, Thunderbird, Apple Mail, or any IMAP/SMTP-compatible client to your AgentMail inbox”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Zero
   Zero✓fullprobed8/10

   Zero's source is publicly hosted on GitHub (Mail-0/Zero) with a full contributing guide, self-hosting instructions, and a verified runtime probe confirming a real, clonable source tree with Docker configs for self-hosting — consistent with an open-source project freely readable by AI-native users. Missing for 10: explicit citation of the license file/name (e.g. MIT/AGPL) to confirm licensing terms.

   • [github] “Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “gives users the power to **self-host** their own email app”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [claimed-docs] “View and edit data with Drizzle Studio pnpm db:studio”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail—none0/10

   No evidence of AgentMail's source code being open or under an open-source license; it is a hosted API/SaaS product with documented API, SDKs, CLI, and MCP server but no mention of source availability or licensing.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Zero
   Zero✓fullprobed8/10

   Multiple GitHub and docs citations explicitly advertise 'Self-Hosting Freedom' and describe running your own email app, and a runtime probe confirms a real self-hostable source tree with docker-compose files for self-hosting deployment. Missing for 10: independent hands-on report of a completed self-host deployment beyond the repo/docker-compose evidence, and more detailed self-host setup documentation.

   • [github] “Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “⚙️ Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “gives users the power to **self-host** their own email app”
   • [github] “⚙️ **Self-Hosting Freedom** – Run your own email app with ease.”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [claimed-docs] “Self-hosting capabilities”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail is presented entirely as a hosted API/SaaS product (docs describe hosted MCP server, hosted API, dashboards) with no documentation of a self-hosted deployment option; a community comment even notes a competitor markets itself as 'a self-hosted drop-in replacement' for AgentMail, implying AgentMail itself lacks this capability.

   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [community] “agentmail charges $20/mo for 10 inboxes. autopilot gives you unlimited inboxes for the cost of a postgres row, positioning itself as a self-…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round to Zero
   Zero~partialclaimed5/10

   Zero's self-hosting capability (own infra, own database via docker-compose) lets a user effectively choose where their data lives, and it claims not to track/collect/sell data, but there is no explicit region/residency selection feature or documented multi-region hosted offering. missing for 10: explicit region/residency selection UI or hosted multi-region options, documentation on data locality guarantees for the hosted SaaS version, independent confirmation of self-host deployment satisfying residency requirements.

   • [github] “Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “⚙️ Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “gives users the power to **self-host** their own email app”
   • [github] “⚙️ **Self-Hosting Freedom** – Run your own email app with ease.”
   • [claimed-docs] “Self-hosting capabilities”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [github] “Zero does not track, collect, or sell your data in any way.”

   proof ↗⚑ flag

   AgentMail—none0/10

   No evidence in the pack mentions data residency, regional storage options, or compliance controls for choosing where data is stored; the docs cover inboxes, messaging, webhooks, MCP, and multi-tenancy but nothing about region selection.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round to Zero
   Zero~partialclaimed5/10

   Zero states it does not track, collect, or sell user data, and self-hosting is available which would let users fully control data flow, implying no AI training on user data. However, there is no explicit statement or policy about AI-model training exclusion (e.g., no clause addressing whether email content sent to AI features like compose/summarize is used for model training). missing for 10: explicit AI-training opt-out/data-use policy, third-party AI provider data-handling terms, independent verification of the no-training claim.

   • [github] “Zero does not track, collect, or sell your data in any way.”
   • [github] “gives users the power to **self-host** their own email app”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”

   proof ↗⚑ flag

   AgentMail—none0/10

   No evidence in the pack addresses data-training opt-out, AI model training policies, or privacy controls regarding use of email data for training; the docs focus on API/product functionality, not data-privacy commitments.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Zero
   Zero~partialclaimed5/10

   Zero claims a no-tracking/no-sell data policy and supports self-hosting (giving users full control over their own data and deletion since they own the infrastructure), plus MCP tools include explicit 'delete emails' actions. However, there's no documented data retention policy, no explicit account/data deletion workflow or export tooling described, and no independent verification of the no-tracking claim. missing for 10: documented retention/export/deletion policy for hosted use, independent audit of data practices, explicit account-deletion or right-to-be-forgotten flow.

   • [github] “Zero does not track, collect, or sell your data in any way.”
   • [github] “gives users the power to **self-host** their own email app”
   • [github] “gives users the power to self-host their own email app while also integrating external services like Gmail and other email providers”
   • [claimed-docs] “Get email threads by ID - List emails in specific folders - Create and send new emails - Create email drafts - Send existing drafts - Delete…”
   • [claimed-docs] “Bulk delete emails - Bulk archive emails”

   proof ↗⚑ flag

   AgentMail—none0/10

   The evidence pack covers AgentMail's inbox/messaging, permissions, and multi-tenancy features but contains no mention of data retention policies, deletion controls, or privacy/compliance settings for stored emails or attachments.

   ⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round to Zero
   Zero~partialprobed5/10

   Zero's GitHub page states it 'does not track, collect, or sell your data in any way,' and self-hosting support (Docker compose files, self-hosting docs) lets AI-native users run their own instance with no vendor telemetry at all. However there is no explicit telemetry settings/opt-out toggle documented, no privacy policy detail, and no independent verification of the no-tracking claim. Missing for 10: explicit telemetry opt-out control/setting, detailed privacy policy, and independent/hands-on confirmation of the no-tracking claim.

   • [github] “Zero does not track, collect, or sell your data in any way.”
   • [github] “Self-Hosting Freedom – Run your own email app with ease.”
   • [github] “⚙️ Self-Hosting Freedom – Run your own email app with ease.”
   • [probe] “PROBE runtime (recorded 2026-09-06): a keyless shallow git clone of Mail-0/Zero landed a REAL self-hostable source tree — repo-root MCP.md (…”

   proof ↗⚑ flag

   AgentMail—none0/10

   No evidence in the pack mentions telemetry, usage tracking, analytics opt-out, or any privacy/data-collection controls for AgentMail; the docs and community items focus on email/API features, pricing, and site performance instead.

   ⚑ flag

Search

1. power-userSearch is fast and precise — operators, filters, and ranked results across my full mail history

   weight 2 · round to AgentMail
   Zero~partialcommunity4/10

   Evidence shows a basic 'search emails with custom queries' and 'filter by labels' capability via the MCP server, but there is no documentation of advanced operators, ranked relevance, or performance/scale across full mail history; a community comment even flags missing basic navigation features, suggesting search UX is still immature. missing for 10: documented search operators/syntax, evidence of ranking/relevance across full historical mail, performance benchmarks, independent hands-on confirmation of search speed/precision.

   • [claimed-docs] “Search emails with custom queries - Filter emails by labels”
   • [community] “hoping to see some more discussion here - i'd love to replace superhuman. However, until Zero has real keyboard navigation, i'll have to wai…”
   • [claimed-docs] “Compose emails with AI assistance - Ask questions about mailbox content - Ask questions about specific email threads - Web search using Perp…”

   proof ↗⚑ flag

   AgentMail~partialclaimed5/10

   Docs confirm full-text search across sender, recipients, subject, and body with relevance ranking, covering the core 'ranked results' and 'across full mail history' aspects. However, there's no evidence of specific search operators (e.g., date ranges, boolean logic) or advanced filters, and no independent benchmarking of speed/precision. missing for 10: documented search operators/filters syntax, evidence of performance at scale, independent verification of search speed/precision.

   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”

   proof ↗⚑ flag

Shortcuts

1. power-userDo everything from the keyboard — comprehensive shortcuts and a command palette — in an interface fast enough to never make me wait

   weight 3 · round to Zero
   Zero!disputedcontradicted2/10

   Zero's own roadmap lists 'customizable keyboard shortcuts' as a planned (not yet shipped) feature, and a hands-on community comment explicitly states the product lacks 'real keyboard navigation' today, directly contradicting any power-user keyboard-first claim; no command palette is mentioned anywhere in the evidence. missing for 10: shipped keyboard shortcut system, command palette, any evidence of interface speed/responsiveness for power users.

   • [claimed-docs] “Customizable keyboard shortcuts”
   • [community] “hoping to see some more discussion here - i'd love to replace superhuman. However, until Zero has real keyboard navigation, i'll have to wai…”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail's docs focus entirely on API/SDK/CLI/webhook/MCP functionality for building agent email workflows; there is no mention anywhere of keyboard shortcuts, a command palette, or any interactive UI navigation features for power users. Community evidence actually describes the dashboard/website as laggy and slow to load (WebGL errors, noticeable lag vs. other sites), directly undercutting the 'fast enough to never wait' requirement even if such an interface existed.

   • [community] “"Application error: a client-side exception has occurred while loading www.agentmail.to"... Failed to create WebGL context... Cookie rejecte…”
   • [community] “The website is really bad. Moving from Python to curl tab on the site shows noticeable lag - I have seen 2-3 whole websites load faster in t…”
   • [community] “I have written about how slow the website is... the amount of lag is something I have genuinely never witnessed in any website... I can't vi…”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”

   proof ↗⚑ flag

Shared inbox

1. team-leadMy team works shared inboxes together — shared accounts or team channels where everyone sees the same conversation state

   weight 3 · round drawn
   Zero—none0/10

   Zero is positioned as a personal AI-powered unified inbox for individual users (Gmail/Outlook accounts), with no evidence of shared inboxes, team channels, or shared conversation state across multiple users; features described are individual email management, MCP tooling, and self-hosting, not multi-user collaboration.

   • [github] “Unified Inbox – Connect multiple email providers like Gmail, Outlook, and more.”
   • [community] “Zero founder describes it as an AI-powered email client that auto-categorizes, summarizes threads, drafts replies, and lets users chat with …”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail's docs describe agent-centric inboxes, cc/bcc human-in-the-loop oversight, drafts for approval, and per-tenant Pods, but nothing indicates a shared inbox/team-channel experience where multiple human team members view the same conversation state together. No evidence of shared inbox dashboards, team member roles, or collaborative conversation views for a team-lead's team.

   • [claimed-docs] “You can cc or bcc a real person on any message your agent sends, creating a "human-in-the-loop" workflow for oversight, escalations, or qual…”
   • [claimed-docs] “create a Pod per customer, give them a scoped API key, and route webhook events to the right place.”
   • [claimed-docs] “Human-in-the-Loop Review: An agent can create a `Draft` for a sensitive or important `Message`, which a human can then review and approve be…”
   • [claimed-docs] “Use `Labels` to track the state of a conversation.”
   • [claimed-docs] “Create one pod per customer/tenant in your system”

   proof ↗⚑ flag

Inbox structure

1. power-userSelect many conversations at once and archive, label, or mark them done in one stroke

   weight 1 · round to Zero
   Zero~partialcommunity4/10

   Zero's MCP docs explicitly list 'Bulk delete emails' and 'Bulk archive emails' plus label modification tools, showing some bulk-action capability, but this is exposed via an AI/MCP tool interface rather than confirmed as a native UI multi-select action, and there's no mention of a 'mark done' state or how many items can be selected/acted on interactively. Community commentary even flags gaps in basic power-user UI ergonomics (no real keyboard navigation), suggesting bulk in-UI triage may be immature. missing for 10: confirmed UI multi-select archive/label/done action, evidence of a 'done' state, independent hands-on confirmation of bulk UI workflow.

   • [claimed-docs] “Modify email labels”
   • [claimed-docs] “Bulk delete emails - Bulk archive emails”
   • [claimed-docs] “Get all user labels - Create new custom labels with custom colors - Delete existing labels”
   • [community] “hoping to see some more discussion here - i'd love to replace superhuman. However, until Zero has real keyboard navigation, i'll have to wai…”

   proof ↗⚑ flag

   AgentMail—none0/10

   AgentMail's docs describe programmatic labeling, threading, and search, but there is no evidence of any UI or bulk API operation for selecting many conversations at once and archiving/labeling/marking done in a single action; the product is positioned as an agent-facing API rather than a human triage inbox with bulk controls.

   • [claimed-docs] “Use `Labels` to track the state of a conversation.”
   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”

   proof ↗⚑ flag