Give Your AI A Memory

Save context once. Reuse it across ChatGPT & Claude.

Every new chat starts with the right background.

Give your AI a memory See setup guide

See a few example prompts by audience

Claude
Why did we switch from REST to gRPC for the internal APIs?
hjarni: get_note
✓
Your notes from the tech review: latency on the order service was 3x worse with JSON serialization. The team benchmarked protobuf and it cut p99 from 120ms to 40ms.
Claude
What did the Series A investors say about our margins?
hjarni: search_notes
✓
From the Sequoia meeting: they wanted gross margins above 70% before raising. You're at 64%.
Claude
What protocol did the Chen lab use for their cell viability assay?
hjarni: search_notes
✓
From your literature notes: Chen et al. used a flow cytometry protocol with 48-hour incubation. 92% viability at the target concentration.
Claude
What was the name of the fisherman I interviewed in Galveston?
hjarni: search_notes
✓
Your interview notes from March 12: Ray Guidry, 34 years shrimping the Gulf. He said the catch is half what it was in the '90s.
See how developers use Hjarni

The problem

Sound familiar?

Claude starts every session from zero

You debugged that race condition last Tuesday. Wrote down the fix. Claude doesn't know. You re-explain the architecture. Again.

Your knowledge is scattered

Architecture decisions in Notion. Post-mortems in Google Docs. That one Slack thread with the deployment fix. Your AI can't see any of it.

Your tools do too much

Notion has 47 features you don't use. Obsidian needs plugins for everything. You just want to write something down and have your AI remember it.

Features

Simple on purpose.

Less software. More thinking.

Built for ChatGPT and Claude

Full REST API and native MCP server. Your AI reads and writes your notes directly. Set up ChatGPT or Claude in minutes.

Share a brain with your team

Shared containers, shared knowledge. Your team's AI knows what the team knows.

Dump ideas fast

The inbox catches everything. Sort later. Don't let organizing slow down thinking.

Connect your thinking

Wiki-links between notes. Build a web of knowledge, not a pile.

Your data is yours

Export everything as Markdown in a ZIP. Always.

Teams

One person writes it down. Everyone's AI knows it.

Share a folder. Everyone's AI catches up instantly.

A shared Hjarni folder with notes written by four different teammates

Write once, the whole team remembers

A teammate documents the deployment fix. Now everyone's AI knows it. No more "did you see that doc?"

Set rules once, the whole team follows

New hires don't start from zero. Their AI already knows your stack and conventions. No more week-one ramp.

Give your team a memory How teams work

Workflow

The loop.

Every new chat starts from zero. Yours doesn't have to.

Claude
Redis pool exhausted on deploy. What should I know before fixing this?
hjarni: search_notes
✓
You hit a similar timeout last January. Fix was bumping max connections and adding a health check.
Bumped to 20 and added the health check. Save what I did.
hjarni: create_note
✓
Saved "Redis pool fix: March 2026" to your Infrastructure folder.
Any other infra issues I should watch for?
hjarni: search_notes
✓
Two notes: a session store memory leak from Redis 6, and a connection spike during the Black Friday load test.
Claude
Planning a trip to Kyoto. What do my notes say?
hjarni: search_notes
✓
Three notes from 2024: Fushimi Inari (go early), Ramen Musubi (9/10), and the bamboo grove at sunrise.
Found a ryokan in Hakone with private onsen for ¥28,000. Save that.
hjarni: create_note
✓
Saved "Hakone ryokan: private onsen, ¥28,000" to your Japan Trip folder.
Any other ryokans I've looked at?
hjarni: search_notes
✓
Two notes: a Kurokawa Onsen stay in 2022, and a Miyajima ryokan you bookmarked but didn't book.
Claude
MRR dropped 8%. What do my notes say about churn?
hjarni: search_notes
✓
Three calls this quarter mention onboarding. Acme Corp, Initech, and Globex all said 3 weeks is too long.
Just got off another call. Same feedback. Save that.
hjarni: create_note
✓
Saved "Churn call #4: onboarding too slow" to your Customer Feedback folder.
What's our onboarding timeline actually look like?
hjarni: search_notes
✓
Target was 5 days, last measured average was 18 days. The bottleneck is the data migration step.
Claude
What did the 2023 paper say about off-target editing rates?
hjarni: search_notes
✓
Zhang et al. reported 0.1% off-target with the high-fidelity variant, vs 1.2% with standard.
Experiment 47: higher dose, tumor volume dropped 34%. Save that.
hjarni: create_note
✓
Saved "Experiment 47: high dose, 34% reduction" to your Lab Journal folder.
What were the results at lower dosages?
hjarni: search_notes
✓
Experiment 31 at low dose showed 18%. Experiment 39 at mid dose showed 26%. Clear dose-response trend.
Claude
What was the angle I had for the climate piece?
hjarni: search_notes
✓
From the pitch meeting: frame it around insurance companies quietly retreating from coastal markets. The "silent withdrawal" angle.
Interviewed the harbor master. 40 years, first flood in '89. Save that.
hjarni: create_note
✓
Saved "Harbor master interview: first flood '89" to your Climate Feature folder.
What other interviews do I have for this piece?
hjarni: search_notes
✓
Three so far: the insurance adjuster in Miami, the city planner from Norfolk, and now the harbor master.

Debug in Claude. Save to Hjarni. Ship the fix. Repeat.

Start your loop How the loop works

Simple pricing

No trials. No hidden fees. Start free and stay free as long as you want.

€ EUR £ GBP $ USD

Free

$0

forever

  • Up to 25 notes
  • Containers, tags & search
  • Full MCP & API access
Get started for free
Most popular

Pro

$10/mo

$99/yr (save 17%)

  • Unlimited notes
  • File attachments
  • Share folders with 2 collaborators
  • Everything in Free
Go Pro

Teams

$13/seat/mo

$129/seat/yr (save 17%)

  • Shared knowledge base
  • Team MCP & API access
  • Member management
  • Billed separately from personal
  • Everything in Pro
Start your team

Frequently asked questions

Is this just another note-taking app?

No. It's a note-taking app your AI can actually use. Your notes become live context for every AI conversation.

Why not Notion or Obsidian?

Great tools. Different goals. Hjarni is built from the ground up for AI. Custom instructions per folder. Team-wide AI conventions. An MCP server designed around your knowledge — not bolted onto a workspace. See how Hjarni compares to Notion, Obsidian, ChatGPT Projects, Claude Projects, and Apple Notes.

What's MCP?

Model Context Protocol. An open standard that lets AI assistants connect to external tools and data. Hjarni has a built-in MCP server. Your AI reads and writes your notes directly.

Which AI assistants work with Hjarni?

ChatGPT and Claude connect via MCP today. Any AI that supports MCP will work automatically. Others can use the REST API.

How do I give my AI a memory?

Add Hjarni as an MCP server in ChatGPT or Claude. Takes two minutes. Every conversation picks up where the last one left off.

Can I control how my AI uses my notes?

Yes. Set custom AI instructions on any folder, team, or your whole account. Your AI follows your conventions. Not its defaults.

Which note-taking apps have a native MCP server?

Hjarni and Notion both ship with one built in. No plugins, no manual export, no copy-paste.

What happens to my data?

Your notes live on our servers. Export everything as Markdown anytime. We don't train AI on your data. We don't sell it. It's yours.

Can I collaborate with others?

Yes. Create a team, invite members, share folders. Everyone's AI benefits from the shared knowledge.

Can I self-host Hjarni?

Not currently. It's a hosted service. That keeps things simple — for you and for us.

Write once. You both remember.

Free to start. No credit card required.

Get started, it's free

Works with Claude and ChatGPT today. Gemini coming soon.