Skills
memwal
by MystenLabs
A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
Our verdict
We have not reviewed memwal yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About memwal
A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
Best for
Developers building AI agents that need reliable, verifiable memory across sessions and apps.
Use cases
- Persist agent state across sessions
- Share memory between different AI applications
- Verify memory integrity for audit or compliance
Notes
133 stars on GitHub. Last updated 2026-11-09. Licensed Apache-2.0.
Indexed from github-skill-md. Verified against the live GitHub repo.
Pros
- Portable and cross-session
- Verifiable memory ensures data integrity
- Full control over memory data
Cons
- Relatively low community traction (126 stars)
- Limited documentation or examples may be available
- Requires TypeScript environment
Key facts
What we have checked
- Days since the last commit
- 1
- GitHub forks
- 48
- GitHub stars
- 137
- Days to a first reply on issues
- 3.6
- Open issues
- 71
- Releases in the last 90 days
- 36
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How memwal is growing
131 to 137
Health and security
Is memwal looked after, and what do its setup files show
Health score
99 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 30 of 30 | Last push 1 days ago |
| Releases | 15 of 15 | 36 releases in 90 days |
| Issue replies | 19.6 of 20 | First reply in 3.6 days (median) |
| Maintainer | 15 of 15 | Owned by an organisation |
| Official source | Not counted | MCP servers only |
Security check static checks
72 out of 100
- High Zod can exhaust memory while validating oversized constrained collections (affects zod 3.25.76, pinned in services/server/scripts/package-lock.json).
- Low esbuild allows arbitrary file read when running the development server on Windows (affects esbuild 0.27.7, pinned in services/server/scripts/package-lock.json).
- Note 1041 files were not read (over 512 KB, or past the 60 file cap): docs/diagrams/interactive_agent-memory-recall_v1.html, docs/diagrams/interactive_agent-memory-write_v1.html, docs/diagrams/interactive_trust-boundary_v1.html and more.
- Note 116 of 292 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.
Alternatives
Alternatives to memwal
| Record | Type | How we know | Checked |
|---|---|---|---|
| claude-mem-installThis is an alternative to it | Skill | Matched from the listing text | |
| Honcho Memory for HermesThis is an alternative to it | Skill | Matched from the listing text | |
| mem-searchThis is an alternative to it | Skill | Matched from the listing text | |
| memory-notesThis is an alternative to it | Skill | Matched from the listing text | |
| para-memory-filesThis is an alternative to it | Skill | Matched from the listing text |
Compare
Compare memwal side by side
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Security finding
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
claude-mem-install
thedotmack
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessi
Honcho Memory for Hermes
Nous Research
Set up and troubleshoot Honcho cross-session memory for Hermes Agent, cloud or self-hosted.
memory-notes
basicmachines-co
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
mem-search
thedotmack
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessi
para-memory-files
paperclipai
The open-source app everyone uses to manage agents at work
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.