Skip to content

Hjarni vs Zep

Zep is a knowledge-graph memory backend for production agents. Hjarni is a Markdown notes app a human writes in. Different buyer, different price floor.

Free to start. No credit card required.

Quick answer

Zep is a context-engineering and agent-memory platform built on a temporal knowledge graph (Graph RAG) for production agents at enterprise scale, with the Graphiti MCP server for read and write access to the graph. Hjarni is a Markdown knowledge base a person writes in, with a built-in MCP server, free to 25 notes and Pro from €9 a month. Pick Zep if you need enterprise-grade, temporally-aware knowledge-graph memory for production agents and have the engineering to run it. Pick Hjarni if you want notes a human writes and owns that any AI can read.

Hjarni Zep
Primary shape

Zep is a developer memory backend built on a graph. Hjarni is a notes app you write in.

Markdown notes you write Temporal knowledge-graph memory
MCP server

Graphiti, Zep's open-source graph engine, exposes an MCP server to add to and search the graph (read and write), working with Claude Desktop, Cursor, and VS Code. Hjarni's MCP server is built into the knowledge base.

Built-in, hosted Graphiti MCP server
Bring your own AI

Both are model-agnostic.

Who writes the content

Zep ingests agent and conversation data into a temporal graph. In Hjarni, a person writes the notes.

You do, in Markdown Your agent, into the graph
Open source and self-host

To self-host you now run the open-source Graphiti framework plus a graph database. The old Zep Community Edition is deprecated. Hjarni is hosted SaaS only, with Markdown export anytime.

Run Graphiti plus a graph DB
Human notes UI

Hjarni is a notes editor a person writes in. Zep is a developer API, not a notes app.

Full Markdown editor
Folder-level AI instructions
Built-in
Hosting region
EU (Germany) Closed SaaS or self-host
Entry price

Zep's free tier is reportedly around 10,000 credits a month and 2 projects; paid Flex starts at $125/mo. Hjarni starts free and Pro is from €9/mo.

Free to 25 notes, Pro from €9/mo Free tier, then from $125/mo
Best fit
Notes a human writes Graph memory for production agents

A knowledge graph vs a knowledge base

Zep is a context-engineering platform for agent memory, built on a temporal knowledge graph. Its open-source engine, Graphiti, turns conversations and data into a graph of entities and relationships that changes over time, so production agents can retrieve temporally-aware context. This is developer infrastructure aimed at scale, not a notes app.

Hjarni is a knowledge base you write in. Notes are plain Markdown, organized in folders, tagged and linked, and the built-in MCP server lets ChatGPT, Claude, and other clients search, read, and update them. The author is a person, and the unit is a note, not a graph node.

Who writes, and at what scale

With Zep, your agent writes into the graph as it runs, and Zep's value is the retrieval and the temporal reasoning over everything it has ingested. That is exactly what you want when an autonomous system needs production-grade memory.

With Hjarni, a person writes the note and any connected AI reads it. There is no graph to model and no ingestion pipeline. You write a runbook or a decision log, and the next time your assistant asks, it reads what you wrote.

Zep is graph memory for agents at scale. Hjarni is the notes a person actually writes.

Different buyer, different price floor

The price tells the story of who each product is for. Hosted Zep is a closed SaaS with a free tier (reportedly around 10,000 credits a month and 2 projects), then paid Flex from $125/mo and up to Enterprise with BYOC and VPC options. To self-host, you now run the open-source Graphiti framework plus a graph database yourself, since the old Community Edition is deprecated. Hjarni starts free at 25 notes, with Pro from €9 a month. One is priced for engineering teams putting agents in production; the other for a person who wants their notes to have a memory.

When Zep is the better fit

If you need enterprise-grade, temporally-aware knowledge-graph memory for production agents, and you have the engineering to run it or the budget for the hosted tier, Zep is built for exactly that. Graph RAG with temporal awareness is a real capability that a full-text notes app does not try to match.

When people choose Hjarni instead

The switch happens when the job is "I want to write notes my AI can read", not "I am running agents in production that need graph memory". Hjarni is the knowledge base and the MCP server in one hosted product, EU-based, with folder-level AI instructions and a free tier. No graph to model, no graph DB to operate. You write a note, your AI reads it.

When to use Zep

  • You need knowledge-graph memory for production agents
  • You want temporally-aware retrieval at enterprise scale
  • You have engineering to run Graphiti, or budget for the hosted tier

When to use Hjarni

  • You want a knowledge base a human writes in, not a graph backend
  • You want a free tier and a low price floor, EU-hosted
  • You want folder-level AI instructions across ChatGPT, Claude, and Cursor

Zep graphs the memory for agents. Hjarni keeps the notes for people.

Common questions

Common questions

What is Zep?

A context-engineering and agent-memory platform built on a temporal knowledge graph (Graph RAG) for production agents at enterprise scale. Its open-source engine, Graphiti, turns conversations and data into a graph that changes over time. It is a developer backend, not a notes app.

Does Zep have an MCP server?

Yes. The Graphiti MCP server lets clients add to and search the graph (read and write), and works with Claude Desktop, Cursor, and VS Code. Hjarni's MCP server is built into the knowledge base. Both are model-agnostic.

How do the prices compare?

They are built for different buyers. Hosted Zep has a free tier (reportedly around 10,000 credits a month and 2 projects), then paid Flex from 125 USD per month. Hjarni starts free at 25 notes, with Pro from 9 EUR per month. Check current pricing on both sides before deciding.

When should I pick Zep over Hjarni?

Pick Zep when you need enterprise-grade, temporally-aware knowledge-graph memory for production agents and have the engineering to run it. To self-host you now run the open-source Graphiti framework plus a graph database, since the old Community Edition is deprecated.

When is Hjarni the better fit?

When the job is writing notes a human owns that any AI can read, not running agents that need graph memory. Hjarni is the knowledge base and the MCP server in one hosted EU product, with folder-level AI instructions and a free tier, and no graph database to operate.

Give your AI a memory

Write once. You both remember.

Free to start. No credit card required.

Works with Claude and ChatGPT today.