memory skill
✓ VerifiedProvides a durable knowledge layer for agents to search, store, and update verified reusable knowledge and project conventions.
- GitHub stars
- 1,663
- Files
- 2
- Last commit
- Nov 9, 2026
- License
- Apache-2.0
- Allowed tools
- —
What does the memory skill do?
memory provides a durable knowledge layer for agents to search, store, and update verified reusable knowledge and project conventions.
Summary generated from the skill's SKILL.md.
About the memory skill
Maintaining a durable knowledge layer for development projects is what this skill enables for AI agents. It allows agents to search for, store, and update verified project conventions, reusable fixes, and architecture rules to prevent repeating mistakes across different sessions. Developers use the memory CLI via npx ai-devkit@latest memory to manage this information, ensuring that non-trivial work is preceded by a search for existing context.
Agents should load this tool when they encounter complex subsystems, error patterns, or specific project constraints that require long-term persistence. The tool produces structured knowledge entries that can be scoped to a global level, a specific project, or a single repository. It relies on a local database, typically located at ~/.ai-devkit/memory.db, to keep information available. Unlike simple chat transcripts, this system enforces a quality gate to exclude secrets, raw logs, and temporary task progress, focusing only on verified, reusable intelligence.
What an agent can do with it
- 1Retrieve project conventionsSearch for established coding standards or architectural rules before starting a new implementation task.
- 2Persist verified technical fixesStore a specific command or debugging pattern that has been confirmed by test results or command output.
- 3Update outdated knowledgeModify an existing memory entry when new evidence from the codebase contradicts the stored information.
- 4Organize knowledge by scopeApply specific technical constraints to a single repository rather than the entire global environment.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the memory skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the memory skill in Claude Code
~/.claude/skills/memory/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/memory ~/.claude/skills/memoryInstall the memory skill in Claude Code (project)
.claude/skills/memory/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/memory .claude/skills/memoryInstall the memory skill in Codex
~/.agents/skills/memory/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/memory ~/.agents/skills/memoryInstall the memory skill in Gemini CLI
~/.gemini/skills/memory/SKILL.md
$ npx degit codeaholicguy/ai-devkit/skills/memory ~/.gemini/skills/memoryInstall the memory skill in Claude.ai
npx degit codeaholicguy/ai-devkit/skills/memory memory && zip -r memory.zip memory # claude.ai → Customize → Skills → + → Create skill → Upload a skill → memory.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablecodeaholicguy/ai-devkit/skills/memory is public and reachablegithub.com/codeaholicguy/ai-devkit/tree/HEAD/skills/memory ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-09github.com/codeaholicguy/ai-devkit/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/codeaholicguy/ai-devkit/blob/HEAD/skills/memory/S ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/codeaholicguy/ai-devkit/blob/HEAD/skills/memory/S ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/codeaholicguy/ai-devkit/blob/HEAD/skills/memory/S ↗Finding
SKILL.md
View on GitHubAI DevKit Memory CLI
Use npx ai-devkit@latest memory ... as the durable knowledge layer.
Workflow
-
For implementation, debugging, review, planning, or documentation tasks, search before deep work unless the task is trivial:
npx ai-devkit@latest memory search --query "<task, subsystem, error, or convention>" --limit 5For broad or risky tasks, search multiple angles: subsystem, error text, framework, command, and task intent.
-
Use results as context:
- Trust repo files, tests, fresh command output, and explicit user instructions over memory.
- If memory conflicts with verified evidence, use the evidence and update the stale memory.
- Mention memory only when it changes the plan or avoids asking the user again.
-
Search before storing:
npx ai-devkit@latest memory search --query "<knowledge to store>" --table -
Store or update only after the quality gate passes.
Quality Gate
Before storing, all must be true:
- Future sessions are likely to reuse it.
- It is verified by code, docs, tests, command output, or explicit user instruction.
- It is not merely a restatement of obvious nearby files unless it prevents repeated agent mistakes.
- It is scoped narrowly enough.
- Existing memory does not already cover it.
- It contains no secrets, credentials, private customer data, personal data, raw logs, or temporary paths.
Store:
- Project conventions, user preferences, durable decisions.
- Reusable fixes, testing patterns, commands, setup gotchas.
- Non-obvious constraints, architecture rules, failure patterns.
Do not store:
- Task progress, transcripts, speculation, generic programming facts.
- Raw errors without diagnosis.
- Anything the user did not intend to persist.
Commands
Search
npx ai-devkit@latest memory search \
--query "<query>" \
--tags "<tags>" \
--scope "<scope>" \
--limit 5
Use --table to get IDs for updates:
npx ai-devkit@latest memory search --query "<query>" --table
Options: --query/-q required; --tags; --scope/-s; --limit/-l from 1-20; --table.
Store
npx ai-devkit@latest memory store \
--title "<actionable title, 10-100 chars>" \
--content "<context, guidance, evidence, exceptions>" \
--tags "<lowercase,tags>" \
--scope "<global|project:name|repo:org/repo>"
Use this content shape when helpful:
Context: Where this applies.
Guidance: What to do.
Evidence: File, command, test, or user instruction.
Exceptions: When not to apply it.
Update
Find the ID with search --table, then update only changed fields:
npx ai-devkit@latest memory update \
--id "<memory-id>" \
--title "<updated title>" \
--content "<updated content>" \
--tags "<replacement,tags>" \
--scope "<updated scope>"
--tags replaces all existing tags.
Scoping
Use the narrowest useful scope:
repo:<org/repo>for one repository.project:<name>for one app, product, or workspace.globalonly for knowledge that applies across unrelated projects.
If unsure, use a narrower scope.
Troubleshooting
- CLI missing: run
npx ai-devkit@latest --version. - Duplicate title: search, then update the existing item if it is the same knowledge.
- Empty results: broaden terms, remove filters, or search symptoms and subsystem names separately.
- Validation error: check title/content lengths, query length, and
--limitrange. - DB path: default is
~/.ai-devkit/memory.db; project config can override it automatically.
Files in this skill
2memory skill questions
How do I install the memory skill in Claude Code?
Run npx degit codeaholicguy/ai-devkit/skills/memory ~/.claude/skills/memory. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the memory skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What should I avoid storing in the memory CLI?
Do not store task progress, transcripts, speculation, generic programming facts, raw errors without diagnosis, or any secrets and credentials.
What are the available scoping options for memory?
You can scope knowledge to a specific repository using repo:<org/repo>, a specific project using project:<name>, or use global for knowledge that applies across all projects.