Skip to content

Rank #1 of 6 in Email Clients & Email AI

AgentMail logo

AgentMail

YC S25

AgentMail · commercial

npm 105.4k/wkpypi 294.1k/wk

Access

Install

pippip install agentmail python-dotenv
npmnpm install agentmail dotenv
npmnpm install -g agentmail-cli

Compare head-to-head

Alternatives to AgentMail

Try itExperimental

See what an agent can do with AgentMail before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -s https://docs.agentmail.to/llms.txt | head -6recorded session — replayed, not live
recorded 2026-09-10 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Accounts openness — stories about accounts openness in this arenaAccounts opennessevidence →

Stories about accounts openness in this arena

24.0/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

63.5/100

Ai email — stories about ai email in this arenaAi emailevidence →

Stories about ai email in this arena

16.0/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

27.6/100

Calendar integration — stories about calendar integration in this arenaCalendar integrationevidence →

Stories about calendar integration in this arena

n/a

Composing sending — stories about composing sending in this arenaComposing sendingevidence →

Stories about composing sending in this arena

0.0/100

Offline reliability — stories about offline reliability in this arenaOffline reliabilityevidence →

Stories about offline reliability in this arena

n/a

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

25.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Privacy tracking — stories about privacy tracking in this arenaPrivacy trackingevidence →

Stories about privacy tracking in this arena

n/a

Search history — stories about search history in this arenaSearch historyevidence →

Stories about search history in this arena

30.0/100

Speed keyboard — stories about speed keyboard in this arenaSpeed keyboardevidence →

Stories about speed keyboard in this arena

0.0/100

Team collaboration — stories about team collaboration in this arenaTeam collaborationevidence →

Stories about team collaboration in this arena

0.0/100

Triage inbox — stories about triage inbox in this arenaTriage inboxevidence →

Stories about triage inbox in this arena

0.0/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 54/54 stories · click a row’s chevron for the rationale and evidence

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full9/10T

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/a0/10

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/auntestednone yet

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10C

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10C

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10C

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1noneuntestednone yet

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial5/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial5/10T

AI drafts replies in my own voice and tone — ready to review and send, not generic boilerplate C

Ai drafting

ai-native userAi email — stories about ai email in this arenaAi email3none0/10

AI triages my inbox for me — auto-labeling, categorizing, and surfacing what needs attention — with behavior I can steer and audit C

Ai triage

ai-native userAi email — stories about ai email in this arenaAi email3none0/10

Connect several accounts across providers — Gmail, Microsoft 365, IMAP — and work them from one place C

Multi account

switcherAccounts openness — stories about accounts openness in this arenaAccounts openness3n/a0/10

Do everything from the keyboard — comprehensive shortcuts and a command palette — in an interface fast enough to never make me wait C

Shortcuts

power-userSpeed keyboard — stories about speed keyboard in this arenaSpeed keyboard3none0/10

My team works shared inboxes together — shared accounts or team channels where everyone sees the same conversation state C

Shared inbox

team-leadTeam collaboration — stories about team collaboration in this arenaTeam collaboration3none0/10

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3none0/10

Split my inbox into focused streams — important, team, newsletters, calendar invites — so triage happens in priority order, not arrival order C

Inbox structure

power-userTriage inbox — stories about triage inbox in this arenaTriage inbox3n/a0/10

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3noneuntestednone yet

An external agent — Claude, ChatGPT, or my own — can read, triage, draft, and send my email end to end through a documented connection C

Agent workflows

ai-native userAi email — stories about ai email in this arenaAi email2full8/10T

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2full8/10T

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

Portability

switcherAccounts openness — stories about accounts openness in this arenaAccounts openness2partial6/10C

Search is fast and precise — operators, filters, and ranked results across my full mail history C

Search

power-userSearch history — stories about search history in this arenaSearch history2partial5/10C

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial4/10C

Ask an assistant questions across my whole inbox and calendar — who said what, what's outstanding — and get grounded answers C

Ai assistant

ai-native userAi email — stories about ai email in this arenaAi email2none0/10

Assign conversations to teammates and route incoming mail with rules so ownership is explicit C

Routing

team-leadTeam collaboration — stories about team collaboration in this arenaTeam collaboration2n/a0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Insert saved snippets or templates — with variables and attachments — instead of retyping the same reply C

Templates

power-userComposing sending — stories about composing sending in this arenaComposing sending2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Read, search, and write email offline, with changes syncing when I reconnect C

Offline

power-userOffline reliability — stories about offline reliability in this arenaOffline reliability2n/auntestednone yet

Schedule an email to send later and undo a send within a grace window C

Sending

power-userComposing sending — stories about composing sending in this arenaComposing sending2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2n/auntestednone yet

See my calendar, respond to invites, and create events without leaving the email client C

Calendar

power-userCalendar integration — stories about calendar integration in this arenaCalendar integration2n/auntestednone yet

Snooze conversations and set follow-up reminders that resurface a thread if nobody replies C

Followups

power-userTriage inbox — stories about triage inbox in this arenaTriage inbox2n/auntestednone yet

The client protects me from senders' tracking — blocking read pixels by default — and is transparent about what it does with my mail data C

Protection

switcherPrivacy tracking — stories about privacy tracking in this arenaPrivacy tracking2n/auntestednone yet

We can discuss an email in an internal side-thread — comments and @mentions beside the message — instead of forwarding copies around C

Shared inbox

team-leadTeam collaboration — stories about team collaboration in this arenaTeam collaboration2n/auntestednone yet

Select many conversations at once and archive, label, or mark them done in one stroke C

Inbox structure

power-userTriage inbox — stories about triage inbox in this arenaTriage inbox1none0/10

Self-host the email app and keep the mail pipeline under my own control C

Portability

switcherAccounts openness — stories about accounts openness in this arenaAccounts openness1none0/10

Import my complete mail history and contacts from my old provider or client C

Migration

switcherSearch history — stories about search history in this arenaSearch history1n/auntestednone yet

See whether and when recipients opened my email C

Sending

power-userComposing sending — stories about composing sending in this arenaComposing sending1noneuntestednone yet

Share my availability or insert bookable meeting times directly into an email C

Calendar

power-userCalendar integration — stories about calendar integration in this arenaCalendar integration1n/auntestednone yet

The same inbox also handles adjacent customer channels — SMS, WhatsApp, social, or live chat — beside email C

Channels

team-leadTeam collaboration — stories about team collaboration in this arenaTeam collaboration1n/auntestednone yet

Use aliases or masked addresses so sign-ups and strangers never learn my real address C

Protection

switcherPrivacy tracking — stories about privacy tracking in this arenaPrivacy tracking1n/auntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1n/auntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 26 stories with headroom

What would move AgentMail’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Ai email — stories about ai email in this arenaAI drafts replies in my own voice and tone — ready to review and send, not generic boilerplate

    nonemoves PA Scoreimpact 30

    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.

  2. Ai email — stories about ai email in this arenaAI triages my inbox for me — auto-labeling, categorizing, and surfacing what needs attention — with behavior I can steer and audit

    nonemoves PA Scoreimpact 30

    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.

  3. Speed keyboard — stories about speed keyboard in this arenaDo everything from the keyboard — comprehensive shortcuts and a command palette — in an interface fast enough to never make me wait

    nonemoves PA Scoreimpact 30

    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.

  4. Openness — open source, data portability, and self-hosting storiesSelf-host the core product

    nonemoves PA Scoreimpact 30

    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.

  5. Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models

    nonemoves PA Scoreimpact 30

    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.

  6. Team collaboration — stories about team collaboration in this arenaMy team works shared inboxes together — shared accounts or team channels where everyone sees the same conversation state

    nonemoves PA Scoreimpact 30

    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.

  7. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    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.

  8. Ai email — stories about ai email in this arenaAsk an assistant questions across my whole inbox and calendar — who said what, what's outstanding — and get grounded answers

    nonemoves PA Scoreimpact 20

    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.

Showing the top 8 of 26 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map19 surfaces · 19 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -s https://docs.agentmail.to/llms.txt | head -6reproduced
$ curl -s https://docs.agentmail.to/llms.txt | head -6
# AgentMail | Documentation

> AgentMail is an email API built for AI agents. Create inboxes, send and receive messages, manage threads, and handle webhooks programmatically.

## Instructions for AI Agents
$curl -sL https://www.agentmail.to/llms.txt | head -6reproduced
$ curl -sL https://www.agentmail.to/llms.txt | head -6
# AgentMail: Email for AI Agents
#
# If you are an AI agent and need email, follow these steps in order:
#
# Step 0: Check if AGENTMAIL_API_[redacted] is already set in your environment.
#         If it is, skip to "Connect" below. You're ready to go.
$curl -si -X POST https://mcp.agentmail.to/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced
$ curl -si -X POST https://mcp.agentmail.to/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401

date: Thu, 10 Sep 2026 19:14:48 GMT

content-type: application/json; charset=utf-8

cf-ray: a390c1fafb19991c-SJC

cf-cache-status: DYNAMIC

access-control-allow-origin: *

etag: W/"18-XPDV80vbMk4yY1/PADG4jYM4rSI"

server: cloudflare

vary: accept-encoding

www-authenticate: Bearer resource_metadata=https://mcp.agentmail.to/.well-known/oauth-protected-resource/mcp

access-control-expose-headers: *

x-clerk-auth-reason: session-[redacted]-and-uat-missing

x-clerk-auth-status: signed-out

x-powered-by: Express

{"error":"Unauthorized"}

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

4 of 9 testable claims verified · 0 contradictedintegrity 44/100

13 distinct capability claims found in AgentMail’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

4

Verified

5

Unverified

0

Contradicted

10

Undersold

Verified (4)
Unverified (5)
Undersold (10)
Claims outside our story set (4)

Real capability claims found in AgentMail’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • Can cc or bcc a real human on agent-sent messages for human-in-the-loop oversight

    source ↗
  • Provides a persistent WebSocket connection for real-time email event delivery

    source ↗
  • Supports creating a dedicated pod per customer with routed webhook events for multi-tenant setups

    source ↗
  • Supports custom sending domains to control sending reputation for production use

    source ↗
Suggest a story for these →

Business model

free-tiersubscriptionusage-basedenterprise-custom

Free tier (3 inboxes, 3k emails/mo); Developer $20/mo and Startup $200/mo with usage limits; custom Enterprise adds BYO cloud, dedicated IPs, SSO. No per-seat API charges.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score44 (Sep 10 '26)46 (Sep 16 '26)
Agent-ready81 (Sep 10 '26)82 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

Data

Agent surface uptime MCP up · llms.txt up · openapi.json up (tracking since Sep 11 '26)