Comparisons
Comparisontheir pages read 22 Sep 2026
Zapier Agents vs attest_tag
Zapier Agents reaches 9,000+ apps through the Zapier directory and counts the month in activities, so the difference is what attest_tag prints and holds: the model and measured cost under every reply, every write held for a Confirm in the thread by default, approver tiers where nobody approves their own request, an audit log in the free plan, and an MIT binary you can run yourself.
Which model answers
Any endpoint, per thread
What a turn costs, and who sees it
Model and cost under every reply
Where it runs
Hosted, or one binary of yours
Who holds the credentials
The proxy. Never the model
Who may approve
Never your own request
What you can audit
Every call, exportable
Pick attest_tag when
- A credential is given to the service, never to the model: sealed with AES-256-GCM under a MASTER_KEY you hold on a self-host, injected by an in-process proxy one hop before the request leaves, and scrubbed from every response before it reaches the model or Slack.
- Any method other than GET, HEAD or OPTIONS is held: the bot posts what it intends to do and a card with Confirm, Cancel and “Something else…”, and the pending write expires after five minutes.
- A monthly budget for the workspace, another per channel, and a per-user hourly rate limit; the bot pauses at the ceiling and says so, rather than reporting having crossed it.
- A write that grants access leaves the thread for an approver's DM, routed to the least powerful tier that covers every call in it; a plan no single tier covers is refused rather than split.
- A flat monthly fee by plan size, never per seat, and every feature in every plan: approval tiers, audit export, budgets, two-factor sign-in and fix jobs are all in the free plan and the MIT binary.
Their page, ours
What the hero says, and what the rest of the site does not.
A hero line is a promise about the product. The questions an engineer asks before rolling one out are usually answered somewhere else on the site — or not answered. These are the ones we looked for.
Zapier Agentstheir hero, verbatim
“Meet your new AI teammates”
Zapier Agents lets you create AI teammates, equipped with company knowledge, that do work across 9,000+ apps on command and on triggers, from a web app, Chrome extension or Slack.
What their pages do not say
- Which model answered a given reply — the AI by Zapier model-tier page names models by tier, but the Agents pages themselves name none
- A cost printed under each reply — usage is a monthly activities counter in the sidebar, and in AI by Zapier a per-run task count
- Whether you can run it yourself, or read the source
- Where the OAuth tokens live, and who holds the encryption key
- Named approver roles, or a rule against approving your own request — the confirmation is the agent owner's
- An audit log on the Free or Professional plan — the pricing page lists it for Team (6 months) and Enterprise (1 year, with Log Streams and an Observability API)
On the public pages listed under the table, as of 22 Sep 2026. An absence is a fact about a page, not about the product; if one of these has since been answered, we will change it.
attest_tagthe same questions, in writing
Which model answers
Any endpoint, per thread
Models and costWhat a turn costs, and who sees it
Model and cost under every reply
Audit and budgetsWhere it runs
Hosted, or one binary of yours
Self-hostedWho holds the credentials
The proxy. Never the model
Credentials, in the guardrailsWho may approve
Never your own request
Access requests and tiersWhat you can audit
Every call, exportable
The audit trail
Side by side
Ten questions worth asking either way.
Our column is the same on every comparison, and each cell ends where the mechanism is shown. Theirs is Zapier Agents’s own pages, quoted or closely paraphrased, as read 22 Sep 2026.
The questionattest_tagZapier Agents
01Which model answers
attest_tag
Any OpenAI-compatible endpoint — OpenRouter, a vendor API, or a model you host. Ships on
Models and costgoogle/gemini-flash, with a heavy model routed to automatically for code and long threads, and a per-thread override.Zapier Agents
Not on the Agents pages. The AI by Zapier model-tier page lists GPT, Claude and Gemini models in Standard, Advanced and Premium tiers — Premium includes GPT-5.4 and Claude 4.8 Opus, Advanced includes GPT-4.1, Claude 4.5 Haiku and Gemini 2.5 Pro — and your own API key on Professional, Team and Enterprise.
02What a turn costs, and who sees it
attest_tag
Metered per completion and printed under the reply beside the model that answered, with
Audit and budgets!usage for the month by channel. A monthly budget for the workspace, another per channel, and a per-user hourly rate limit — the bot pauses at the ceiling rather than reporting having crossed it.Zapier Agents
“Zapier Agents displays your activity usage in the left sidebar”: a monthly activities counter, 400 on Free and 1,500 on Pro, capped at 10 or 40 per run. A cost printed under each reply is not stated.
03Where it runs
attest_tag
Hosted by us, or one MIT-licensed Go binary with the console embedded on your own infrastructure — Docker, Cloud Run, Fargate, Container Apps or Kubernetes. The same code either way. Where HIPAA applies, run it yourself so nothing leaves your network, and we sign a business associate agreement with you.
Self-hostedZapier Agents
Hosted by Zapier: “Zapier is hosted on Amazon Web Services (AWS) in the United States.” A self-hosted or on-premises option is not stated on their site.
04Who holds the credentials
attest_tag
The service, never the model. Sealed with AES-256-GCM at rest — under a key you hold, on a self-host — injected by a proxy at the network edge, and scrubbed back out of every response before it reaches the model or the thread.
Credentials, in the guardrailsZapier Agents
“Data is encrypted at rest using AES-256”; the security page lists “Managed connections — company-owned credentials” as a governance feature and the pricing page lists “Managed app connections” under Enterprise. Where OAuth tokens and API keys are held, who holds the encryption key and who can view a credential are not stated.
05Before it changes something
attest_tag
Any method other than GET, HEAD or OPTIONS is held for a card in the thread — Confirm, Cancel, or say what you actually wanted. Pending writes expire after five minutes. A fix job opens a draft pull request and never merges.
Human-in-the-loop writesZapier Agents
A confirm step is written into the agent's instructions: “ask for my confirmation through [messaging app] before continuing to the next instructions.” In AI by Zapier, “Require approval before running” can be turned on per tool. A hold on every write is not stated.
06Who may approve
attest_tag
Writes that grant access leave the thread and go to an approver’s DM. Nobody approves their own request — enforced three times over, once in SQL — and a request routes to the least powerful tier that covers every call in it.
Access requests and tiersZapier Agents
“Your confirmation” — the agent's owner, who returns “to Zapier Agents to approve or stop the workflow.” For Zaps, a Human in the Loop step routes approval by email or Slack. Named approver roles, and a rule against approving your own request, are not stated.
07What you can audit
attest_tag
Every turn, tool call, proxied request and completion — with tokens and cost — in a console you run, exportable as CSV. Self-hosted, it is a table in your own database.
The audit trailZapier Agents
“Zapier provides audit logs that track user and automation activities.” On the pricing page the audit log row reads 6 months for Team and 1 year for Enterprise, with Log Streams and an Observability API on Enterprise; not listed for Free or Professional.
08Source and licence
attest_tag
MIT. The repository is the product: the hosted service runs the same binary you can clone, read and build.
The same binary, inside your networkZapier Agents
Not stated on their site.
09What it costs
attest_tag
A free plan that does not expire — $5 of model spend a month — then a flat monthly fee by plan size, $49 for up to 10 users to $599 for up to 250 users, with AI credit included. Never per seat, and every feature in every plan.
PricingZapier Agents
Per account by task or activity allowance, not per seat. Agents: 400 activities a month on Free, 1,500 on Pro, custom on Enterprise. Zapier plans: Free 100 tasks; Professional 750 tasks at $19.99 a month annual or $29.99 monthly; Team 2,000 tasks from $69.00 annual; Enterprise through Sales.
10Where it lives
attest_tag
Slack and Microsoft Teams, from one console: channels, threads and DMs in Slack; channel reply chains, group chats and one-to-one chats in Teams. It joins the channels you invite it to, and there is no second place for the team to go.
Threads and streamingZapier Agents
A web app at agents.zapier.com and a Chrome extension; Slack through Zapier triggers and actions — “This agent provides timely responses to new questions in the IT helpdesk Slack channel” — with approvals “through [messaging app]”.
“Not stated on their site.” means we read the pages below on 22 Sep 2026 and did not find it — not that the product lacks it. Ask them; a vendor that answers all ten in writing is a good sign about the vendor. If we have something wrong, tell us and we will fix the page.
Pages read: Zapier AgentsZapier pricingZapier Agents pricingZapier help: How is Zapier Agents usage measured?Zapier help: Migrating from Agents to AI by ZapierZapier help: Add approval steps to your agent's instructionsZapier security and complianceZapier help: AI by Zapier model tier pricing
Questions
What people ask about Zapier Agents and attest_tag.
Is attest_tag an open-source alternative to Zapier Agents?
Yes. attest_tag is MIT-licensed: one Go binary with the admin console embedded, one database, and a public repository on GitHub. The hosted service runs the same code you can clone and build. Zapier's Agents, pricing and security pages, read on 22 September 2026, do not state a licence or whether the source is available; Zapier's help centre says Agents is being folded into AI by Zapier in the Zap editor.
Can I run attest_tag on my own servers, and can I run Zapier Agents?
attest_tag self-hosts as one binary: Docker on a laptop or VM, Google Cloud Run, AWS Fargate, Azure Container Apps, or Kubernetes with a Helm chart. Self-hosting has no fee and no limits set by us, and the audit log is then a table in your own database. Zapier's security page says “Zapier is hosted on Amazon Web Services (AWS) in the United States”; a self-hosted or on-premises option is not stated on the pages read.
Which model does Zapier Agents run on, and which does attest_tag?
attest_tag calls any OpenAI-compatible endpoint — OpenRouter, a vendor API, or a model you host — ships on google/gemini-flash, and lets the model be set per workspace, per channel and per thread. The Zapier Agents pages name no model; the AI by Zapier model-tier page lists GPT, Claude and Gemini models in Standard, Advanced and Premium tiers, defaulting to Premium on paid plans, with your own API key on Professional, Team and Enterprise.
What does a reply cost on Zapier Agents and on attest_tag?
attest_tag records every completion's measured tokens and cost and shows them under the reply; !usage shows the month by channel against the budget. A typical answered question on the default model costs about $0.002, a fix job about $0.18. Zapier Agents counts activities — “any billable action that your agent takes” — against a monthly allowance of 400 on Free and 1,500 on Pro, shown in the sidebar; a cost under each reply is not stated.
Does Zapier Agents hold a write for a human before it runs?
Zapier's help centre says you can write a sentence into the agent's instructions — “ask for my confirmation through [messaging app] before continuing to the next instructions” — and the agent alerts you to return to Zapier Agents to approve or stop. In AI by Zapier, “Require approval before running” can be turned on per tool. attest_tag holds any method other than GET, HEAD or OPTIONS for a Confirm card in the thread, expiring after five minutes.
Can someone approve their own request in Zapier Agents or attest_tag?
Not in attest_tag. A write that grants access leaves the thread and goes to an approver's DM with Approve and Deny, routed to the least powerful tier that covers every call in it, and nobody approves their own request — enforced three times over, once in SQL. In Zapier Agents the confirmation is “your confirmation”, the agent owner's; named approver roles, or a rule against approving your own request, are not stated on their pages.
More comparisons
The same ten questions, asked of the others.
- vs ViktorAn AI coworker you @mention in Slack and Microsoft Teams, with its own computer in the cloud, connections to 3,200+ tools, and a pause for approval in the thread before sensitive actions.
- vs DustA platform for creating, sharing and running agents that connect your company knowledge, tools and teams, mentioned as @Dust in Slack or triggered from Slack workflows.
- vs LindyLindy is an AI teammate that connects to your tools, knows about your company and does work for the whole team, from Slack DMs and channels or as scheduled routines.
- vs RunbearRunbear puts AI teammates into Slack, Microsoft Teams and Discord channels, where they answer @mentions and direct messages and act through connected tools. It is priced by credits rather than seats.
- vs Slack AISlack’s built-in AI features and agents, sold with paid Slack plans and working inside Slack: “a powerfully simple way to be more productive, built with knowledge from your company.”
- vs ChatGPT for SlackOpenAI’s app for chatting one-on-one with ChatGPT in a dedicated Slack sidebar — summarising threads, drafting replies, searching Slack — with a companion ChatGPT Agents app for channels.
- vs DevinAn AI software engineer that ships pull requests the way your team does; you tag it in Slack or assign it a ticket in Linear.
- vs GleanAn enterprise AI platform that connects to a company's work apps and data sources to provide search, an assistant and agents across surfaces that include Slack and Microsoft Teams.
- vs GumloopAn AI agent platform where anyone at a company builds, shares and controls agents that connect to their apps and run on triggers, deployable to Slack channels and Microsoft Teams.
- vs MoveworksMoveworks is an AI Assistant platform for an entire workforce to search and act across business applications, reached through chat, web, intranets, service portals and mobile.
- vs OnyxOnyx is an open-source platform that connects to your enterprise knowledge and gives humans and agents context, with a chat and search UI, custom agents and a Slack bot.
- vs Relevance AIA platform for building and running “specialist agents for every task”, which its site calls “The home of the AI Workforce”, with agents that answer an @mention in Slack.
- vs Claude TagAnthropic’s own Slack teammate: Claude, hosted for you, first-party inside Slack.
Try both
Run both in the same channel for a week.
We mean it. attest_tag answers in threads, so it will not collide with whatever else is in the channel, and a week of your own questions settles this faster than any table.
Half an hour to set up, one channel to start, and the free plan needs no card. See what it costs.