Product knowledge, with receipts

Everything your team knows, with the source attached.

Mari connects the tools where your product knowledge already lives, GitHub, Slack, Confluence, Jira, your help center, and turns them into one record your team can ask. Answers come with citations. Facts come with an owner and a freshness date. When a source changes, Mari flags what leaned on it. It runs in your cloud, and it does one job: knowledge.

Run it yourself, or have us run it: in your cloud, or hosted.

Apache 2.0 · 12 connectors · your cloud or ours

mari/ overviewwatchingdemo data
47ChangesThis week
6Facts to reviewAwaiting verification
3Workflows activeCodified from runs

Today's review

6 open
  • DRVerify the new proration rule in the billing runbookFact check
  • MGApprove the SSO onboarding guide for publishApproval
  • PKRetire two stale screenshots in auth/READMEStale
What it does

One job: product knowledge.

01
Connect what you already have

12 connectors: GitHub, Slack, Google Drive, Confluence, Notion, Jira, Airtable, Asana, Dropbox, Linear, Trello, and your Zendesk help center. Drop in files too. Mari reads them in place and re-syncs as they change. Nothing to migrate, no new tool for the team to learn.

02
Ask, and get the source with the answer

Search and chat over everything connected. Answers stream with numbered citations back to the doc, commit, or thread they came from, so a support rep or a new hire can check before they repeat it.

03
Know who stands behind a fact

Facts carry an owner, a verification state, and a freshness date. Approved answers are the ones your team signed off on. Unsigned assertions show up as exactly that.

04
See what a change touched

A lineage graph ties documents, commits, PRs, and decisions together. When a source changes, Mari flags the facts that leaned on it and routes them to their owner.

05
Put it where people ask

@mention Mari in Slack and it answers from the record. @mention it on a GitHub pull request and it checks the change against what's known. Point an MCP client or a knowledge chat at the same record. The agent in the console can tag, approve, sync, and edit, with each action in the audit trail.

Use cases

Where Mari earns its keep.

01Support

Answer from the record, not from memory

A customer asks whether the API supports it. The rep @mentions Mari in Slack and gets the answer with the doc it came from and the PR that changed it. No tap on an engineer's shoulder.

02Support

Retire the answers that stopped being true

Every support team has a pile of saved replies nobody dates. In Mari an approved answer carries an owner and a freshness date, and gets flagged when the source behind it moves.

03Product managers

Find out before the customer does

Eng cut the feature last sprint. The help center still promises it. Mari flags the fact and routes it to its owner before the next call, not after.

04Developers

Stop being the search engine

Every "where's the doc for" lands on whoever remembers. Point people at Mari instead. It cites its sources, so nobody has to take your word for it or interrupt your afternoon.

05Developers

Catch the docs the repo left behind

The repo audit scans connected repositories for documentation drift, coverage gaps, and stale pages, and offers one-click fixes that pull the missing docs in.

06Leaders

Answer the questionnaire from the record

Each fact carries its source, owner, and sign-off. The security review stops being archaeology: filter the registry and hand it over.

Is Mari for you?

For teams whose knowledge outran their docs.

Wikis and search tools store and find what someone once wrote. They can't tell you who owns it, whether anyone checked it, or whether the source has since moved on. Mari does that part, and only that part. If any of these read like your week, it will earn its keep.

01

One person is the documentation

Every hard question routes to the engineer who remembers. Their answers are correct, unwritten, and unavailable the week they take off.

02

The same question, answered five ways

Support asks in Slack, engineering points at a Confluence page, product corrects both in a DM. Three answers, none written down, and the customer got the first one.

03

Nobody knows which page is current

The wiki holds six stale pages for every good one, and new hires learn to distrust all of them. Search finds all six with equal confidence.

04

Your AI tools answer from whatever they can reach

The coding agent, the support bot, the chat in Slack: each one repeats what it retrieved, with no idea whether it's canonical, approved, or two releases old.

What Mari doesn't do

Mari is the knowledge layer, not the whole stack. It won't write your marketing, run your help desk, replace your wiki, or take over your coding agent. It connects to those, keeps the record of what's known, who owns it, and whether it still holds, and hands the answer, with its source, to whatever asks. If your problem is a good corpus that deserves a prettier website, a publishing platform will make you happier than we will.

AI removed the cost of writing. It didn't remove the cost of being wrong.

The whole org

A source, an owner, a sign-off on each fact. Or it gets flagged.

Mari is the record of what your team knows, org-wide. Three problems it exists to stop, each with a demo below:

tap a problem below to open it

An answer arrives with no paper trail.

Six months on, nobody knows where a fact came from or whether the source still says it. Once every tool in the company answers questions, "says who" stops being answerable.

How Mari solves it · Semantic Lineage

Mari pins each fact to the source it came from, the doc, the commit, the thread, the reviewer, and forward to everything downstream that reused it.

source
api/refresh.ts
source
sla-policy.v4
fact
MR-4821
fact
MR-4825
published
docs/auth
published
rfp-answer
published
status-page
tracing api/refresh.ts → downstream
scroll to explore
5 stages · one record
  1. 01connect the source
  2. 02capture the fact
  3. 03check it against the source
  4. 04owner signs off
  5. 05watch for drift

A fact with no owner is just a rumor with better formatting.

The dashboard

One dashboard over what your team knows.

mari/ overviewwatchingdemo data
47ChangesThis week
6Facts to reviewAwaiting verification
3Workflows activeCodified from runs

Today's review

Showing 1 to 4 of 7 tasks · 6 open
TaskStatus
Verify the new proration rule in the billing runbookOpen
Approve the SSO onboarding guide for publishOpen
Retire two stale screenshots in auth/READMEDone
Review the incident escalation ladderOpen

Source pulse

Last 7 days
GitHub128 commits
Slack412 messages
Notion19 edits
Google Drive34 files

Live activity

Running
  1. Docs guardrail completed a run over billing/*.md42s ago
  2. Dana R. refined Pricing FAQ3m ago
  3. Mari verified a fact in Proration rule6m ago
  4. Notion synced Onboarding space25m ago
  • Support

    You answer the same question forty times a week from a saved reply you didn't write, and learn it was wrong when the customer replies with a screenshot.

    with mariAsk Mari in Slack and get the answer with its source. Approved answers carry an owner and a date, and get flagged when the product moves on.

  • Product managers

    You find out on the customer call that the help center promises a feature eng cut two sprints ago. You own what the product says everywhere, and none of the pages.

    with mariWhen the product changes, Mari flags the pages that leaned on it and routes the fix to its owner. You stop being the human changelog.

  • Developers

    Every question about how it works routes to you, and the doc you'd point at was true two releases ago.

    with mariMari cites the doc, the commit, and the PR, so people check the source instead of you. The repo audit finds the pages that fell behind.

  • Leaders

    You sign off on what the company publishes with no way to see it. Then a security review asks who approved a number, and the answer is a week of archaeology.

    with mariOne dashboard over every fact's source, owner, approval, and freshness. The audit trail exists before anyone asks for it.

8 in 10

companies will have shipped generative AI by 2026

source · Gartner
30%

of outbound messages will be synthetically generated, per Gartner

source · Gartner
AI TRiSM

trust, risk & security management is a named Gartner priority

source · Gartner
Trust

In your cloud, on your terms.

Mari is open-source software, Apache 2.0. Run it yourself, have us run it inside your VPC, or have us host it. Your data lives where you decide.

The full security page →
Runs where your data lives

A Docker Compose stack with Postgres and pgvector, in your VPC. Local models through ollama are optional, and every feature has a deterministic fallback without them.

Your credentials, your sources

Connectors read with tokens you create and can revoke, scoped to what you choose to share. Sources stay where they are: Mari syncs, it doesn't migrate.

A record you can hand over

Each fact carries its owner, sign-off state, and freshness, and answers cite their sources. A review gets receipts, not recollections.

Ready for procurement

A custom MSA, DPA, and a security review with your team come with the paid plan.

FAQs

The questions you'd ask before you trust it.

The product
Running it
Get started

Three ways in.

Pricing

Pay for the operations, not the software.

Mari is Apache 2.0. Run it yourself for free, or have us run it on the enterprise plan, in your cloud or ours. Pricing scales with your team, not your stack.

Self-hosted

Free/ Apache 2.0, forever

The open-source product, on your infrastructure. Clone it, compose up, connect a source, and the record is yours to run.

  • 12 connectors, cited answers, facts with owners, lineage, and drift audits
  • Docker Compose, Postgres with pgvector, optional ollama for local models
  • Slack bot and GitHub webhooks, self-serve
  • The console and the agent, with the audit trail
  • Community support (GitHub)

Bring your own cloud

Custom/ enterprise, annual

We deploy, run, upgrade, and maintain Mari inside your VPC. Your data and access stay in your account. You get the record without the operations.

  • Everything in Self-hosted, plus the enterprise features
  • We own the operations, inside your VPC
  • Data and access stay in your account
  • A dedicated solutions engineer, from rollout onward
  • Onboarding for support, product, and engineering
  • Custom MSA, DPA, and security review

Hosted

Custom/ enterprise, annual

We operate the deployment in an environment we run, and your team signs in. Nothing to provision on your side.

  • Everything in Self-hosted, plus the enterprise features
  • We own the operations, in an environment we run
  • Where it runs, who can reach it, and retention set out in the MSA and DPA
  • A dedicated solutions engineer, from rollout onward
  • Onboarding for support, product, and engineering
  • Custom MSA, DPA, and security review

Custom procurement, on-prem, or a different shape entirely? Book a call and we'll figure it out.