reme-memory

name	reme_memory
description	Use ReMe as a file-native long-term memory system through the reme CLI.

ReMe Memory

Use ReMe as the persistent memory layer for this Agent. ReMe stores raw sessions, daily notes, resources, and long-term digest memories in a local workspace. Prefer ReMe for information that should survive across conversations.

Before Use

• ReMe should already be running with reme start.
• If a command fails because the service is not running, tell the user to start ReMe.
• Use CLI commands directly; do not edit the workspace files by hand unless the user explicitly asks.

Useful health checks:

reme find_reme
reme health_check
reme version

Retrieval

Before answering questions about previous conversations, user preferences, project history, decisions, resources, or long-term context, search ReMe first:

reme search query="<question or keywords>" limit=5

When search results point to a useful file, read the relevant file or range:

reme read path="<workspace-relative-path>"
reme read path="<workspace-relative-path>" start_line=1 end_line=80

Use traverse when wikilink neighbors may matter:

reme traverse path="<workspace-relative-path>" depth=1 direction=both

Writing Memory

Record memory when the conversation includes durable facts, user preferences, important decisions, project context, or lessons learned. Avoid storing secrets or sensitive personal data unless the user explicitly requests it.

For ordinary conversation memory, call auto_memory with the current conversation messages and a stable session id:

reme auto_memory \
  session_id="<session-id>" \
  messages='[{"role":"user","content":"..."},{"role":"assistant","content":"..."}]' \
  memory_hint="<why this should be remembered>"

For direct file operations, use ReMe file jobs:

reme write path="daily/<YYYY-MM-DD>/<name>.md" name="<name>" description="<description>" content="<markdown>"
reme edit path="<workspace-relative-path>" old="<old text>" new="<new text>"

Read before editing, and preserve existing content unless replacing it is explicitly intended.

Resources

External documents should be placed under resource/YYYY-MM-DD/. ReMe background watchers normally process new resource files after reme start.

To trigger resource processing manually:

reme auto_resource changes='[{"path":"resource/<YYYY-MM-DD>/<file>","change":"added"}]'

Long-Term Consolidation

auto_dream consolidates daily notes and resource interpretations into long-term digest memories. It can run from cron in ReMe, or be called manually when the Agent framework owns the schedule:

reme auto_dream date="<YYYY-MM-DD>"

Use proactive to read interest topics generated by auto_dream:

reme proactive date="<YYYY-MM-DD>"

proactive only returns topics; the Agent decides whether and how to mention them to the user.

Integration Rules

• Any Agent framework can integrate ReMe through this skill plus the reme CLI.
• Background and cron jobs run automatically after reme start.
• Hook jobs require explicit Agent lifecycle integration: call auto_memory after useful conversation turns, auto_resource after resource ingestion, auto_dream on a schedule or user request, and proactive before generating proactive suggestions.
• QwenPaw 2.0 will integrate the new ReMe flow directly.
• A Claude Code plugin is planned for lower-friction setup.