What does claude --continue do?

It picks up the most recent session in the directory you are standing in. claude --resume shows a list and lets you choose instead. For closing the terminal and carrying on an hour later, nothing improves on it.

Why can I not see sessions from another directory?

The list is scoped to the current directory. Work done in a sibling repository, or in the same repository from a different path, never appears in it.

Can claude --continue find something from last month?

Not usefully. It resumes a session from a list of recent ones; it cannot answer which session touched a given file, where an error was solved, or what was decided six weeks ago. That is a search problem rather than a resume problem.

Does it see sessions from Codex, Cursor or OpenCode?

No. Those transcripts sit in different folders in different formats, and the built-in has no knowledge of them in any form.

Can the assistant check its own history without me asking?

Not with the built-in, which only runs when you run it. With the MCP server registered, the assistant queries the index itself mid-task instead of waiting to be told.

What claude --continue does not do

claude --continue is free, already installed, and good enough much of the time. It resumes one session, in one tool, in the directory you happen to be standing in.

Updated 22 September 2026

What the built-in already covers

claude --continue picks back up the most recent session in the current directory, and claude --resume lets you pick from a list instead. For "I closed the terminal an hour ago and want to keep going," that's the right tool, and nothing here improves on it.

Where it stops working

One directory	The list is scoped to wherever you're standing. Work done in a sibling repo, or in the same repo from a different path, never shows up.
One tool	It knows nothing about the session you ran in Codex or OpenCode, because that transcript lives in a different format, in a different folder entirely.
Resume, not search	You pick from a list of recent sessions. There's no way to ask which session touched a given file, where a particular error got solved, or what was decided about a design six weeks ago.
You have to ask	Resuming only happens when you do it deliberately. The assistant can't check its own history mid-task, because it has no tool that lets it.

What actually fills the gap

Nothing replaces the built-in — keep using it for the same-day, same-directory case. The gap it leaves is recall, and recall is fundamentally a search problem:

what --continue cannot answer

$ chat-recall search "why did we drop the pooler"
  every session, every tool, ranked

> what was I working on yesterday?
  the assistant answers from the index, across all of them

And once the MCP server is registered, the assistant runs those queries itself instead of waiting to be told to.

The honest comparison

Same session, same day, same directory	Use claude --continue. It's free and it's already sitting right there.
Something from last month	Search. Scrolling through a list of recent sessions won't find it.
Something you did in another tool	Search. The built-in can't see it at all, in any form.
Letting the assistant check for itself	MCP. The agent queries the index directly instead of you pasting results back in.

Start free, no card How it works

Questions

What does claude --continue do?	It picks up the most recent session in the directory you are standing in. claude --resume shows a list and lets you choose instead. For closing the terminal and carrying on an hour later, nothing improves on it.
Why can I not see sessions from another directory?	The list is scoped to the current directory. Work done in a sibling repository, or in the same repository from a different path, never appears in it.
Can claude --continue find something from last month?	Not usefully. It resumes a session from a list of recent ones; it cannot answer which session touched a given file, where an error was solved, or what was decided six weeks ago. That is a search problem rather than a resume problem.
Does it see sessions from Codex, Cursor or OpenCode?	No. Those transcripts sit in different folders in different formats, and the built-in has no knowledge of them in any form.
Can the assistant check its own history without me asking?	Not with the built-in, which only runs when you run it. With the MCP server registered, the assistant queries the index itself mid-task instead of waiting to be told.

More notes

Where every AI coding tool stores your sessions on disk	Exact paths and formats for every AI coding tool chat-recall reads: and the retention period that quietly deletes them.
Does Claude Code remember previous sessions?	Partly, and the part it forgets is the expensive one. What CLAUDE.md, auto memory and --continue each carry across, and what none of them carry.
Claude Code has auto memory. Where it stops.	Auto memory writes notes about your preferences per repository, on one machine. What it is good at, the four boundaries it does not cross, and what to pair it with.