mem
Skill1 starsChanged 5 months agoMITView on GitHub
Manage persistent memory — project context, session notes, cross-session knowledge retention
3 other projects use a version of this.
Adopted by
Most recently taken up by
- sdsrss/claude-mem-litetheir own version, first seen Nov 1, 2026
- agenticexpert/skillstheir own version, first seen Aug 19, 2026
- liorhai5/ai-memorytheir own version, first seen Mar 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- sdsrss/claude-mem-lite★ 68same name
- agenticexpert/skills★ 2same name
- liorhai5/ai-memory★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository84 other files it gives its agents.
- api-design-reviewerSkill
- api-test-suite-builderSkill
- ask-mattSkill
- aws-solution-architectSkill
- captureSkill
- changelog-generatorSkill
- ci-cd-pipeline-builderSkill
- cloud-securitySkill
- codebase-designSkill
- codebase-onboardingSkill
- code-reviewerSkill
- context-compressSkill
- context-modeSkill
- database-designerSkill
- database-schema-designerSkill
- dependency-auditorSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- env-secrets-managerSkill
- finish-branchSkill
- firecrawlSkill
- focused-fixSkill
- frontend-designSkill
- get-shit-doneSkill
- git-guardrails-claude-codeSkill
- git-worktree-managerSkill
- git-worktreesSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- incident-commanderSkill
- incident-responseSkill
- mcp-builderSkill
- migration-architectSkill
- monorepo-navigatorSkill
- observability-designerSkill
- performance-profilerSkill
- playwright-testingSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-gainSkill
- ponytail-helpSkill
- ponytail-reviewSkill
- ponytailSkill
- prompt-engineeringSkill
- prototypeSkill
- pr-review-expertSkill
- rag-architectSkill
- red-teamSkill
- reflectSkill
- resolving-merge-conflictsSkill
- root-cause-tracingSkill
- runbook-generatorSkill
- self-evalSkill
- senior-architectSkill
- senior-backendSkill
- senior-devopsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 64
Before re-exploring or re-deriving:
- Distinctive: line 80
Remove entries no longer relevant
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Memory Manager
Maintain persistent knowledge across sessions. Remember what matters, forget what doesn't.
Memory System
File Locations
| File | Purpose | Lifetime |
MEMORY.md (project) | Project context, rules, architecture | Cross-session |
notes.md (session) | Free-form observations, quotes, questions | Per-session |
MEMORY.md (global) | User preferences, cross-project patterns | All projects |
What Goes Where
MEMORY.md (Project):
- Architecture decisions and rationale
- Coding conventions and rules
- Known patterns and anti-patterns
- Technology-specific guidance
- Durable facts that survive sessions
notes.md (Session):
- Quotes with lasting value
- Unresolved questions
- Cross-project observations
- Notes for future-self
- Context that won't fit in tasks
MEMORY.md (Global):
- User coding preferences
- Cross-project methodology rules
- Style preferences
- Tool preferences
When to Write to Memory
Write to MEMORY.md When:
- User states a project-level rule
- Architectural decision is made
- Durable fact discovered that spans sessions
- Pattern established that should persist
Write to notes.md When:
- Interesting observation but not yet decided
- Quote worth remembering
- Question to revisit later
- Cross-project similarity noticed
DON'T Write When:
- Task-specific details (use task progress)
- Temporary state (use checkpoint)
- Ephemeral debugging notes
- Things already in memory
Reading Memory
Before re-exploring or re-deriving:
- Search memory for relevant keywords
- Read MEMORY.md for project context
- Check notes.md for session observations
- Only then explore codebase
Memory Maintenance
At Checkpoints:
- Review what was learned
- Promote durable facts to MEMORY.md
- Clean up notes.md (remove resolved items)
Periodically:
- Review MEMORY.md for outdated info
- Remove entries no longer relevant
- Consolidate related entries
Anti-Patterns
| Pattern | Problem |
| Not searching before exploring | Re-deriving known facts |
| Putting everything in MEMORY.md | Bloat, hard to find |
| Putting durable facts in notes.md | Lost at session end |
| Not writing decisions to memory | Repeated discussions |
| Storing task-specific details in memory | Noise, not signal |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.