Runic
MEMORY

The conversation follows your account

Chat history, archived summaries and checkpoints are stored per account, so the agent remembers across sessions and devices.

Try it free →Read the docs

Stored with the account

The conversation — live messages, archived stretches and the checkpoints inside them — is one record per account on the server. It loads when you open the editor and saves 600 ms after every change. Sign in from another browser and the same chat is there. Delete your account and it is deleted with it. There is one conversation per account, across all your documents; the panel header always says which document you are working on, and every proposal remembers which document it belongs to.

A live window and an archive

Each request carries the recent conversation verbatim. When that window grows past roughly 6,000 tokens, the older messages fold into an archive and only a short summary stays in play; the newest eight messages are never archived. The summary is written by Claude Haiku 4.5 in two to four sentences — what you asked, what changed, decisions and open points — and if that call fails, a deterministic note takes its place (“12 earlier messages, starting with: …”). Archiving never waits on AI.

In the panel an archive shows as “📦 12 archived” followed by its summary. Click the row to expand the original messages; applied proposals inside still offer ↩ Restore. Up to 20 archives are kept.

Recall when you refer back

Summaries alone would lose detail, so Runic also recalls. Your new message is broken into words of four letters or more and compared with every archived message; any archived message sharing at least two of those words comes back verbatim, best three first, under “RECALLED MESSAGES”. The model is told to treat both summaries and recalled messages as things that really happened in this conversation — and, when a detail exists only in a summary and was not recalled, to ask for it rather than invent it.

Recall is plain word overlap, deliberately: no embeddings, no hidden state. If you refer to “the escalation step”, the message that mentioned escalation is the one that comes back.

What travels with each request

The live window — recent messages, each trimmed to 1,500 characters and 24,000 in total, never more than the last 30; up to six archive summaries of 1,200 characters each; up to three recalled messages; and the first 16,000 characters of the current document. Proposal bodies are never repeated in history — a message that carried a diff is sent as a bracket note like “[proposed an edit to ‘Onboarding’ — applied]”, because the document itself already travels with the request.

Limits

“Clear” removes everything, including archives and checkpoints. The saved record is capped at 400 KB; archiving drops the text payloads of unapplied proposals to stay well under it. Memory is not per document: switching documents does not switch conversations. Older builds kept the chat in the browser; on first load Runic migrates that copy to the account and removes the local one.

How to use it

  1. Chat as usual
    Nothing to set up. Once the conversation outgrows its window, a “📦 N archived” row appears above the live messages with a summary.
  2. Expand an archive when you need it
    Click the row (▸ / ▾) to read the original messages or to reach an older ↩ Restore.
  3. Refer back in your own words
    Use the words you used before — “the retry loop we discussed for payments” — and the matching archived messages are recalled for that request.
  4. Ask it to act on earlier suggestions
    “Apply what you suggested” builds the edit from the conversation instead of asking you to restate it.
  5. Pick up on another device
    Sign in anywhere; the same conversation and checkpoints load with your account.
  6. Start over
    “Clear” in the panel header wipes the conversation and its archives.

Commands & shortcuts

📦 N archivedan archived stretch; click to expand or collapse
↩ Restore (inside an archive)checkpoints stay usable after archiving
Clearwipe live messages, archives and checkpoints

Tips

  • Name things consistently in chat. Recall is word overlap, so the noun you used the first time is the noun that brings the message back.
  • You do not have to re-paste a suggestion: “do that” and “update it with what you suggested” are understood.
  • If the agent replies that it needs a detail, that detail sat in an archive summary and was not recalled; give it in one line and continue.
  • The header says which document you are working on — check it before applying a proposal after switching documents.

Questions

Is the conversation per document?

No, it is one conversation per account. Each proposal remembers its own document, and Apply only works on the document it was made for.

Where is the chat stored?

In Runic’s database, one record per user, saved shortly after every change. It follows your account to any browser and is deleted with the account.

Can I change when archiving kicks in?

The live window budget is about 6,000 tokens. There is no settings control for it; the client reads an optional chatArchiveTokens value (minimum 500) from the runic.prefs entry in the browser’s local storage if you set one.

Does the agent see archived messages?

It sees their summaries on every request, and the original messages when your request shares words with them. It is told never to invent details a summary does not contain.