Zeca's memory

Zeca can remember you, your projects and what your agents did. It is off until you turn it on, is kept on this computer, and only you write it.

Turning it on

#

Turn it on in Settings → Chat & voice → Memory → Zeca’s memory. The app then keeps a journal in the local vults.sqlite for 90 days: each agent turn’s time, steps and changes, each card’s answer with its command or path, and the lines of Zeca’s chat, secrets redacted before anything is written. The section’s other switches appear once this one is on.

Off, nothing of the memory reaches a model (no facts, no recall, no journal): the Memory beside the Nest’s Chat shows only Zeca’s memory is off…, By project shows no memory facts, and /remember is refused. Turning it off stops the writing and keeps what was written.

What Zeca remembers is a git repository of small Markdown files in ~/.local/share/vults/memory/, each change a commit. Settings → Activity → Clear history removes the journal and what derives from it, but not that folder (what it removes): to erase his facts, delete it.

What joins a conversation

#

When a conversation starts, his memory joins it after his instructions: who you are, what he learned, how to speak to you, and the memory of the project it works in. It stays fixed for the whole conversation; a fact added meanwhile joins the next one. Turning the memory off doesn’t take it from a conversation already running; reopened later from the list, it starts without his facts.

Before each message, the app searches the journal and the days’ summaries for what your words are about, on this computer, and up to three passages join the message as the <memories> block, context and never instructions. Today’s chat is left out, and so is anything a conversation said after it read content from outside. The passages go to the chat’s provider with your message. The API chat can also ask for more with its recall tool, and suggest a fact with memory_propose, which only writes a proposal.

Writing his memory

#

• /remember <fact> in the chat, with the memory on, saves a fact to what Zeca learned; /remember project: <fact> to the project the conversation is in. /forget <words> removes the one fact that holds them (with several, it lists them).
• What Zeca proposes waits in the Memory beside the Nest’s Chat, with where it goes (a project by its name and folder) and the change as a diff: Remember saves it, Turn down drops it.
• The Memory also lists what he remembers, file by file with how full each is, and the history: who wrote each change (you, or Zeca with your yes) and Undo, which takes it back in a new change (refused when a later change touched the same file; never offered on one Vults did not write).

A fact never gets in twice: /remember and every proposal are refused when another fact already says it, case, spaces and the final stop aside, and the same fact decided in the last month is not proposed again. A proposal passes the memory’s scan (no hidden characters, no words that address a model, no key shapes).

What he does on his own

#

Each is a switch under Settings → Chat & voice → Memory, off until you turn it on. Haiku is Claude Code’s smallest model, through your claude and subscription, with no tools and none of your settings; each call goes through the network gate and the local trace (Safety).

The summary runs in an hourly pass: each past day without a summary, up to three a pass (it catches up after days away), three tries per day while the app runs. The embeddings run in that pass, for each summary without one, and before each chat message (ollama pull nomic-embed-text first).

The sleep comes once a day, from two in the morning and while nothing is working. Even without its switch, it proposes removing a fact that repeats another in its section, with no model. With it, it also proposes merges and writes the debrief, in your language, marked as his reading of the summaries. Every change waits for your yes.

Project memory

#

The Nest’s Activity → By project has a card for each repository a session works in: its folders and branches, its sessions, your pull requests and checks (from the GitHub card), and what Zeca remembers of the project. It reads only this computer. A conversation that starts in a repository brings that memory along.

Sharing AGENTS.md with Claude

#

When a repository has an AGENTS.md (the project memory Codex reads) that its CLAUDE.md does not import, its card offers Share it with Claude…. It shows the change (@AGENTS.md added at the end of CLAUDE.md, @../AGENTS.md at the end of .claude/CLAUDE.md, or a new CLAUDE.md) and writes it only when you click Apply, over the very file you saw, after a dated backup in ~/.local/share/vults/backups/. Then Claude Code and Codex read the same project memory.

Through Claude Code

#

The chat hands Claude Code Zeca’s own MCP server, vults-zeca, with --mcp-config (your Claude config is never touched): flock_list (your sessions now), recall and journal_day (his journal), roost_memory (the project’s memory) and memory_propose; only flock_list with the memory off. Claude Code asks with a card before each call your rules don’t allow, and a proposal still waits in the Memory tab. These calls do not mark the conversation as having read outside content. The server is this app run again (vults --zeca-mcp), and sends nothing anywhere: flock_list reads a redacted snapshot of the island’s sessions the app keeps while it runs and removes when it quits, and the journal calls read vults.sqlite without ever upgrading it. Codex reads MCP servers only from its own config, so it does not get them.