How do I give my team's Claude or ChatGPT a shared knowledge base?
Create a team in Hjarni and put the context your team keeps re-explaining into shared Markdown folders: one folder each for runbooks, decisions, onboarding, architecture, and customer interviews. Give each folder its own AI instructions, such as "search this folder first and follow the steps exactly". Then every teammate connects the AI they already use to the team knowledge base through Hjarni's built-in MCP server. A teammate on Claude and a teammate on ChatGPT read and write the same notes, because the shared memory lives in Hjarni rather than inside either product. Start with runbooks and decisions; those two folders pay for themselves fastest.
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
OnboardingEach 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.
This page is the short version. For the full walkthrough, per-seat pricing, and the roles and permissions model, see Hjarni for Teams.