Comparisons
Comparisontheir pages read 22 Sep 2026
Glean vs attest_tag
Glean puts one search and assistant over a company's apps on every surface, so the difference is what happens once an agent acts inside Slack: attest_tag holds every write for a Confirm in the thread unless an admin's allow rule clearly covers it, routes a grant to an approver who is never the requester, prints model and cost under every reply, lets you change the model per thread, and ships as an MIT binary you can run for nothing.
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
- Any method other than GET, HEAD or OPTIONS is held in the Slack thread for a card with Confirm, Cancel and “Something else…”, and a pending write expires after five minutes.
- A credential is injected by an in-process proxy one hop before the request leaves; the model only ever emits a URL and a method, and responses are scrubbed of anything secret-shaped before they reach the model or Slack.
- 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 flat monthly fee by plan size, never per seat, and every feature — approval tiers, audit export, budgets, two-factor sign-in, MCP servers, fix jobs — in the free plan and the MIT binary alike.
- “Fix this and raise a PR” hands the change to a separate worker container that clones the branch, runs the tests before and after the change, and opens a draft pull request; it pushes one branch and never merges.
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.
Gleantheir hero, verbatim
“Enterprise AI that understands your company”
An 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.
What their pages do not say
- What a turn cost, shown to the person who asked
- Where the OAuth tokens and API keys live
- A licence, or source you can read
- What a seat costs, in dollars
- Which model answered a given reply
- A separate approver for a write that grants access, who is never the requester
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 Glean’s own pages, quoted or closely paraphrased, as read 22 Sep 2026.
The questionattest_tagGlean
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.Glean
Bring your own keys for providers, or use Glean’s Universal Model Key for pre-procured models with guardrails. The Model Hub lists 40+ open and proprietary LLMs from OpenAI, Google and Amazon Bedrock. Whether the model is named under a reply is not stated.
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.Glean
Model Hub usage is priced per million tokens on their docs pricing page, and their Model Hub page says you can set usage limits to manage spend; a cost shown to the person who asked a question 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-hostedGlean
Customer-hosted deployment in your own GCP or AWS tenant, or Glean-hosted on a single-tenant architecture; hosting is “Included in seat fee for Glean Hosted customers”. A downloadable binary or on-premise install is not stated.
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 guardrailsGlean
Not stated on their site.
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 writesGlean
“Write actions in agents running in the Glean web app pause for user approval before executing.” Their docs add that this is available only in interactive web-app sessions and that it “[l]eaves Slack and Microsoft Teams behavior unchanged”; agent builders may set specific steps to “Run without user confirmation” when the workflow is safe to auto-run in the web app.
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 tiersGlean
The person running the agent, in the web app: “Allow: let the agent proceed with the write step.” A separate approver, or a rule against approving your own request, is 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 trailGlean
Admin audit logs capture administrative actions — changes to connectors, roles, configuration, agent subscriptions and action executions — filterable by time range, user and action type, exportable to CSV or streamed to a SIEM. Listed under Glean Protect, included in the seat fee.
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 networkGlean
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.
PricingGlean
“Licensed on a per-user, per-month basis” for the Glean Core Suite; no per-user dollar figure is published. Model Hub usage is priced per million tokens — Glean’s “Waldo” model at $0.50 input and $2.50 output. The site offers “Get a demo” and “Contact 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 streamingGlean
Browser, desktop app, mobile app, Slack, Microsoft Teams, Zoom, GitHub, Miro, a sidebar and a companion, all listed under the seat fee. In Slack: “Chat directly with Glean in Slack to surface answers from past messages, documents, and company-wide knowledge.”
“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: Glean homepageGlean Protect / SecuritySlack agents with GleanLLM Model HubGlean Core Suite pricing (docs)Human-in-the-loop confirmations for write tools (docs)Core security principles (docs)Supported LLMs (docs)Glean pricing page (resolves to the homepage)
Questions
What people ask about Glean and attest_tag.
Is attest_tag an open-source alternative to Glean?
attest_tag is an open-source AI teammate for Slack and Microsoft Teams under the MIT licence: one Go binary with the admin console embedded, one database, and a public repository that the hosted service runs unchanged. Glean’s pages describe a hosted or customer-cloud-hosted enterprise platform for search, an assistant and agents across many surfaces; they do not state a licence or whether the source is available. The two overlap where an agent answers and acts from Slack or Microsoft Teams.
Can I run attest_tag on my own servers?
Yes. The same binary the hosted service runs goes on your own infrastructure: Docker on a laptop or VM, Google Cloud Run, AWS Fargate, Azure Container Apps, or Kubernetes via Helm. Self-hosting has no fee and no limits set by us; the MASTER_KEY that seals credentials is one you hold, and the audit log is a table in your own database. Glean’s pages offer hosting within your own GCP or AWS tenant; a downloadable binary is not stated.
Which model does each run on?
attest_tag runs on any OpenAI-compatible endpoint — OpenRouter, a vendor API, or a model you host — and ships on google/gemini-flash. The model is set per workspace and per channel, and overridden per thread with !model, and a heavy model is routed to automatically for code, long threads and turns that reach eight tool calls. Glean’s Model Hub lists 40+ LLMs from OpenAI, Google and Amazon Bedrock, with your own keys or Glean’s Universal Model Key; which model answered a reply is not stated.
What does a turn cost?
On attest_tag, every completion’s tokens and cost are measured and printed under the reply; !usage shows the month’s spend by channel against the budget. A typical question on the default model costs about $0.002, a fix job about $0.18, and the bot pauses at the workspace or channel budget and says so. Glean’s docs price Model Hub usage per million tokens and their Model Hub page says you can set usage limits to manage spend by user, agent or department; a cost shown to the person who asked is not stated.
Does Glean hold a write for a human before it runs?
In the Glean web app, yes: their docs say write actions in agents pause for user approval before executing, that this is available only in interactive web-app sessions, and that it leaves Slack and Microsoft Teams behaviour unchanged; agent builders may set specific steps to run without user confirmation. attest_tag holds any method other than GET, HEAD or OPTIONS in the Slack thread for a card with Confirm, Cancel and “Something else…”; a pending write expires after five minutes.
Can someone approve their own request?
Not on attest_tag. A write that grants access leaves the thread and goes to an approver as a DM with Approve and Deny; 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. On Glean, their docs describe the person running the agent in the web app choosing Allow; a separate approver or a rule against self-approval is not stated.
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 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 Zapier AgentsZapier 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.
- 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.