Memory Management
SkillDocs & knowledgeGuides your agent to remember lessons across chats and route them into memory, skills, scheduled tasks, or tape.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Memory Management skill
About this capability
Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.
What this skill tells your AI
The instructions your AI receives, as published by thinkinaixyz/deepchat in resources/skills/memory-management/SKILL.md and read by ahel’s review.
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.
Procedures -> Skill
When the useful learning is a reusable multi-step procedure, prefer drafting a skill with skill_manage instead of stuffing the full procedure into Memory. Memory may keep a short pointer or heuristic, but the repeatable workflow belongs in a Skill.
Use skill_manage for draft skills only. Do not modify installed skills unless the user explicitly asks through the supported review flow.
Recurring -> Scheduled Task
When the user asks for a periodic, low-frequency, or future recurring action, suggest creating a Scheduled Task in settings. Memory does not wake the agent, schedule future work, or create automation side effects.
End-of-task Learning Check
Before finishing a non-trivial task, check whether there is one durable lesson to save:
- Did the user reveal a stable preference or constraint?
- Did you learn a durable project fact?
- Is there a task outcome, blocker, or explicit deferral worth preserving?
- Did a reusable heuristic work?
- Did an anti-pattern or stale assumption become clear?
- Is this actually a reusable procedure for
skill_manageor a recurring need for Scheduled Tasks rather than Memory?
Remember only the smallest durable conclusion. Leave raw process in Tape.
Signals
- GitHub stars
- 6k
- Forks
- 732
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
memory-management-thinkinaixyz- Source
- github.com/thinkinaixyz/deepchat