Memory

Memory is what the agent remembers about a project between sessions. Not the conversation - that's a session - but the durable, non-obvious facts worth carrying forward.

Good memory entries look like:

"The API client is generated; edit openapi.yaml, never client.ts."
"We use pnpm, not npm. npm install breaks the lockfile."
"Integration tests need docker compose up -d first."

How it works

The agent writes memory itself when it learns something durable, and reads it back into the system prompt on later runs. It's scoped per project.

Three tools drive it, and only the write prompts for approval:

Tool	Approval
`memory_list`	No
`memory_read`	No
`memory_write`	Yes

Because writes prompt, nothing enters memory without you seeing it.

Where it lives

Under <project>/.jan/agent/memory/, as files. You can read them, edit them, delete them, or commit them. Nothing is hidden in an opaque store.

Retrieval is backed by the same store Jan Desktop uses for memory, so a fact learned in one is available in the other.

Memory is shared with Jan Desktop. Settings you change there apply to what the terminal agent recalls, and vice versa.

Keeping it useful

Memory works when it's small and specific. A note that restates what any reader would see from the README is noise; a note about the thing that surprised someone is worth keeping.

If the agent has stored something wrong, delete the file. There's no special command for it - they are just files.

Memory and AGENT.md

They overlap, and the distinction is who writes them:

	Written by	Best for
`AGENT.md`	You	Rules you want followed every time
Memory	The agent	Facts it discovered and shouldn't have to rediscover

If you find yourself correcting the same thing repeatedly, promote it into AGENT.md where it's guaranteed to be in the prompt.

Subagents Skills