Mmcp.market

Superlocalmemory MCP server

by varun369·io.github.varun369/superlocalmemory·v2.7.5·226 stars
No reviews yet

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

C60/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C60/100

full report

Adoption
Established

226 stars1.4k downloads/wk

Reviews

Write one

Nobody has reviewed Superlocalmemory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Superlocalmemory tools (12)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • backup_status

    Get auto-backup system status for SuperLocalMemory.

  • build_graph

    Build or rebuild the knowledge graph from existing memories.

  • correct_pattern

    Correct a learned pattern that is wrong. Use get_learned_patterns first to see pattern IDs.

  • fetch

    Retrieve full content of a memory by ID.

  • get_learned_patterns

    See what SuperLocalMemory has learned about your preferences, projects, and workflow patterns.

  • get_status

    Get SuperLocalMemory system status and statistics.

  • list_recent

    List most recent memories.

  • memory_used

    Call this tool whenever you use information from a recalled memory in your response. This is the most important feedback signal — it teaches SuperLocalMemory which memories are truly useful and dramatically improves future recall quality. All data stays 100% local.

  • recall

    Search memories using semantic similarity and knowledge graph. Results are personalized based on your usage patterns — the more you use SuperLocalMemory, the better results get. All learning is local.

  • remember

    Save content to SuperLocalMemory with intelligent indexing.

  • search

    Search for documents in SuperLocalMemory.

  • switch_profile

    Switch to a different memory profile.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

1 high2 medium
  • Code scan87 source files scanned3/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 16 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Findings (3)

  • mediumnpm install lifecycle script presentinstall.script
  • highNetwork call to a paste/tunnel/webhook hostnet.suspicious-host
    configs/chatgpt-desktop-mcp.json: …": "Copy the HTTPS URL from ngrok (e.g. https://abc123.ngrok.app)", "step4": "In ChatGPT: Settings →…
  • mediumnpm install lifecycle script presentinstall.script
    package.json: …'*.pyc' -delete 2>/dev/null; true", "postinstall": "node scripts/postinstall.js", "pre…
Overall 60/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Install Superlocalmemory in Claude Code, Cursor or VS Code

Runs npx -y superlocalmemory on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add superlocalmemory -- npx -y superlocalmemory
Add to Cursor

What the publisher says

From the Superlocalmemory repository's README, as published. We do not edit it. Read it on GitHub

SuperLocalMemory V4.1.17

Rent the LLM. Own the memory.

Rent an LLM — but own the memory, for your company and for your industry.

The governed memory layer for AI agents: local-first, auditable, and built for the compliance obligations teams now actually carry. Models are interchangeable and rented by the token. What your agents remember is yours — it is your customers' data, your retention obligations, and your audit trail. SLM keeps that layer on infrastructure you control, with multi-workspace isolation, role-based access, and GDPR + EU AI Act governance controls built in.

The boundary. SuperLocalMemory starts with a local runtime; provider-backed enrichment, cloud backup, connectors, and proxy use are explicit choices. Different products solve different boundaries. Published benchmark evidence carried into V4 comes from the published V3 research architecture; it is not a claim of a newly rerun V4 package benchmark.

How to check that, rather than believe it. Every reliability guarantee here is stated as a falsifiable invariant, tested under an adversarial condition with a negative control, and shipped with the harness that regenerates the evidence: python benchmark/runall.py --trials 200 --output-dir results/. What each experiment does not exercise is stated too. v4.1.17 — one control plane: SLM-Mesh peer coordination · multi-scope memory (personal / shared / global) · profiles · Cache · Compress · 7-layer retrieval · code graph · Entity Explorer · skill evolution · Modes A/B/C · GDPR retention & audit chain · bounded loops — across CLI, MCP, dashboard, the Claude plugin, the Codex add-on, and documented IDE integrations. Proxy: slm wrap claude  ·  MCP: add slmcompress to your config  ·  Skill: zero-config Four public arXiv preprints · V4: arXiv:2608.08253 · companion archive: Zenodo 21853302 (DOI 10.5281/zenodo.21853302) · prior preprints: 2603.02240 · 2603.14588 · 2604.04514.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Superlocalmemory: common questions

Is Superlocalmemory MCP server safe?
With care: it is graded C, so read the findings first (60/100). Read the Superlocalmemory safety report
How do I install Superlocalmemory?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Superlocalmemory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Superlocalmemory maintained?
The last commit was 24 days ago (2026-09-12). The latest release is v2.7.5.
What can I use instead of Superlocalmemory?
Servers from other publishers that do the same job: M3 Memory MCP server, Shodh Memory MCP server and Reverie MCP server. Compare all Superlocalmemory alternatives.

Alternatives to Superlocalmemory

Same job from other publishers: the closest match first, then the best rated.

All Superlocalmemory alternatives →
  • M3 Memory
    Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@10, hybrid search, GDPR, no cloud.
    A
  • Shodh Memory
    Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
    C
  • Reverie
    Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
    B
  • Octobrain
    Persistent memory for AI assistants with semantic search and knowledge graph relationships.
    More from Muvon →
    A
  • Sverklo
    Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.
    C
Superlocalmemory vs M3 MemorySuperlocalmemory vs Shodh MemorySuperlocalmemory vs Reverie

More from varun369 →