# Memory Management

Guide the agent to recall, remember, and route durable learning into Memory, Skills...

- Repository: https://github.com/ThinkInAIXYZ/deepchat (6384 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add ThinkInAIXYZ/deepchat --skill memory-management -g -a claude-code -y`
Codex: `npx skills add ThinkInAIXYZ/deepchat --skill memory-management -g -a codex -y`
Cursor: `npx skills add ThinkInAIXYZ/deepchat --skill memory-management -g -a cursor -y`
Gemini CLI: `npx skills add ThinkInAIXYZ/deepchat --skill memory-management -g -a gemini-cli -y`

## Description

Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Memory Management

Use this skill when a task may produce durable learning or when the user asks you to recall, remember, continue earlier work, preserve an exact statement, capture a reusable procedure, or handle a recurring need.

## Recall

Rely on automatic memory injection for ordinary context. Use `memory_recall` when the user refers to previous work with cues such as again, last time, before, continue, same project, remember, or asks what you already know.

Use `tape_search` and then `tape_context` when the user needs source evidence, exact wording, logs, command output, file snippets, or why a prior decision was made. Memory is a durable conclusion layer, not the raw transcript.

## Remember

Use `memory_remember` only for durable conclusions that should change future behavior. Choose the most specific category:

- `user_preference`: stable user preferences, constraints, communication style, environment choices.
- `project_fact`: durable project conventions, architecture entry points, commands, dependencies, paths, or operational constraints.
- `task_outcome`: completed, blocked, or deliberately deferred task results. Include status, outcome, and blocker in prose when relevant.
- `heuristic`: reusable troubleshooting strategy, workflow, decision rule, or engineering lesson.
- `anti_pattern`: repeated mistake, unsafe approach, brittle pattern, stale assumption, or thing to avoid.

Do not remember raw tool results, bash output, grep output, file contents, transient mechanics, one-off failures, secrets, credentials, hidden reasoning, or anything only useful for the current turn.

## Verbatim Scope

Store exact wording only when the user explicitly asks you to remember a sentence or phrase verbatim. In that case, keep the requested text intact and make the surrounding content minimal.

Automatic extraction is different: it should normalize durable facts into concise memory content, deduplicate related entries, and avoid preserving raw transcript text.

The rest: https://github.com/ThinkInAIXYZ/deepchat/blob/HEAD/resources/skills/memory-management/SKILL.md