Skip to content

Hjarni for Teams

A shared knowledge base that Claude and ChatGPT can actually read. One place for the context your whole team keeps re-explaining.

Product example

Onboard a new hire without interrupting a senior engineer

When your runbooks, decisions, and architecture live in Hjarni, every teammate's AI answers from the same context. New hires ask their AI first.

Claude
I'm new here. How do we deploy to production?
hjarni: search (Runbooks)
✓
From the team's Deploy runbook: merge to main, CI runs, then run bin/deploy production. It tags the release and runs migrations before the cutover. Deploys are paused on Fridays.
What if a migration fails halfway?
The runbook says roll back with bin/deploy rollback, then post in the incident channel. The Decisions folder notes why migrations are kept backward compatible for one release.

Claude answers a new engineer's deploy question using the team's shared notes in Hjarni.

The problem

Everyone on your team re-explains the same context to their AI. One person has the runbook. Another has the decision log. A third has the onboarding notes. None of it is connected, and none of it carries across conversations.

The pain scales with headcount. A new hire opens Claude and asks "how do we handle deploys?" Claude does not know. A founder asks ChatGPT "what did we decide about pricing last quarter?" ChatGPT does not know. Every conversation starts from zero.

What a team knowledge base looks like

Team Knowledge Base
  Architecture
  Conventions
  Decisions
  Runbooks
  Customer Interviews
  Onboarding

Each folder ships with its own AI instructions. On Runbooks: "When asked about deploys or incidents, search this folder first and follow the steps exactly."

Onboarding for new hires

The hardest part of joining a team is the unwritten context. Why this service exists. Why that other one was sunset. The reason you use Postgres. In most teams that lives in three Slack channels, one doc, and one person's head.

Write it down once. A new engineer connects Claude to Hjarni and asks "walk me through how the billing service works." Claude reads the Architecture folder and the decision log, then walks them through it. The senior engineer was not interrupted.

Runbooks the AI can read

A runbook in a wiki is read by humans, slowly, at three in the morning. A runbook in Hjarni is read by Claude or ChatGPT, instantly, when someone asks. Put your deploy steps, rollback procedures, and incident playbooks in a Runbooks folder. Add a folder-level instruction. Your team's AI becomes the first responder.

This is not magic. It is documentation that AI can read. The work is still writing the runbook. What changes is who reads it.

Decision logs as institutional memory

The decisions your team makes are the most valuable knowledge you produce, and the easiest to lose. Why you picked Postgres. Why you moved off Redis. Why pricing went from per-seat to flat. What you tried and rejected.

Write them down once and put them in a Decisions folder. From then on, when anyone asks Claude or ChatGPT "why do we do X this way," the answer comes from your decision log, not from guesswork. This is the institutional memory most companies lose every time someone leaves.

Your team's AI starts from zero. Yours doesn't have to.

What makes it different

  • AI-native, not AI-added. The MCP server is built in. Every folder can carry its own AI instructions that Claude and ChatGPT follow.
  • Personal and shared together. Personal notes stay personal. The team knowledge base is shared.
  • No bundled AI. Teammates bring their own ChatGPT or Claude. No per-message costs. No per-seat token limits from Hjarni.
  • Simple on purpose. Notes, folders, and a connection to your AI. No databases, kanban boards, or page builders.

Built for small teams first

Built for teams where the same few people keep explaining the same few decisions, runbooks, and customer facts to every AI they use. Small technical teams, founders, and indie SaaS. If you need SSO and an audit log, those are available on the Enterprise side too.

Common questions

Questions teams actually ask

How does a team share AI context in Hjarni?

A team gets a shared knowledge base. Architecture, decisions, runbooks, and onboarding notes live in shared folders, and every teammate's ChatGPT or Claude reads the same notes through MCP. Nobody re-explains the same context to their own AI.

Do all teammates need their own AI subscription?

Yes. Hjarni gives the AI a memory. The AI itself is whichever client each person uses, such as ChatGPT, Claude, Cursor, or Copilot. There is no bundled AI and no per-message cost from Hjarni.

Can a note be both personal and shared?

No. A note belongs to either your personal space or a team. You can move notes across as needed, but a note lives in one place at a time.

Can different teammates set different AI instructions?

Team-level instructions are shared, so the whole team's AI follows the same rules in a given folder. Personal instructions stay personal to each member.

How does Hjarni help onboard new hires?

A new hire connects their AI to the team knowledge base and asks it to walk through how a service works or how deploys run. Claude or ChatGPT reads the Architecture and Decisions folders and answers, so the senior engineer is not interrupted on day one.

Give your AI a memory

More use cases

Hjarni for Developers Hjarni for Researchers Hjarni for Founders Hjarni for Writers Hjarni for Travelers

Write once. You both remember.

Free to start. No credit card required.

Give your AI a memory

Works with Claude and ChatGPT today. Gemini coming soon.