MCP.Market

KEPTA — the memory for AI systems MCP server

by DamianTodorovic·io.github.DamianTodorovic/kepta·v3.4.0·2 stars
No reviews yet

Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

2 stars606 downloads/wk

Reviews

Write one

Nobody has reviewed KEPTA — the memory for AI systems yet.

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

KEPTA — the memory for AI systems tools (8, 2 write)

write = sends, deletes, buys or posts

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

  • memory_consolidate

    Finds duplicates and contradictions, returns candidate pairs. Nothing changes until dryRun:false with confirm:"supersede". Undo via memory_update supersededBy:null.

  • memory_deletewrite action

    Moves a note to the trash and returns trashed:true; permanent:true deletes the row. Way back: memory_list with trash:true shows the id, then POST /api/memories/:id/restore.

  • memory_forget

    Invalidates one note and returns it: expire closes validTo at the current time, supersede re-points to supersedeBy, delete trashes it. Undo by clearing validTo or supersededBy.

  • memory_graph

    Reads entities and the [[links]] between them, around one entity or the capped whole graph, and returns entities and relations. Read-only; memory_search finds the notes themselves.

  • memory_list

    Lists notes with count, total and pages, newest first. Private notes are never listed, even when scope asks for them. Read-only; use memory_search to find something by meaning.

  • memory_save

    Saves a note and returns its id; [[Wiki links]] become entities. With id it replaces the whole note - memory_update patches, memory_delete trashes. duplicateWarning names a twin.

  • memory_search

    Searches by words, vectors and links. Returns hits with score and dates; private notes never appear. Count 0 can mean a just-saved note is still indexing - run it again. Read-only.

  • memory_updatewrite action

    Patches one note and returns it; only the fields you send change - memory_save with an id replaces the whole note. supersededBy:null undoes a wrong memory_consolidate.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –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 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How KEPTA — the memory for AI systems compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 3,470 Web search servers
Tools
8
the typical Web search server has 5
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 70% of 1,786 Web search servers
Downloads a week
606
more than 88% of 827 Web search servers with a package

What its tools let an agent do: 6 read · 2 change

Release history: 17 versions in the registry since 2026-09-11, latest 2026-10-13, typically one every 1 day.

Install KEPTA — the memory for AI systems in Claude Code, Cursor or VS Code

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

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

What the publisher says

From the KEPTA — the memory for AI systems repository's README, as published. We do not edit it. Read it on GitHub

KEPTA Core

Your AI assistant forgets everything. Every chat starts from zero.

KEPTA is the fix: one local, encrypted memory that every assistant reads and writes — Claude Desktop, Cursor, Gemini CLI, Cline, any MCP client, and scripts over HTTP. No cloud. No account. One file you own.

KEPTA is a local memory for AI assistants. Documents, decisions and client knowledge go into an encrypted knowledge base on your own computer — and your assistant (Claude Desktop, Cursor, any MCP client) recalls it as if it had never forgotten.

This repository is the open core (AGPL-3.0): the memory engine, the MCP server, the HTTP API — and the Python client, which is MIT so any Python project can embed it. The full desktop application is KEPTA Pro.

flowchart LR
  subgraph Apps["Your AI apps — any of them"]
    A["Claude Desktop"]
    B["Cursor · Gemini CLI<br/>Cline · Codex · Zed · …"]
    C["Your scripts"]
  end
  K["keptа-mcp<br/>MCP stdio + browser UI"]
  E[("KEPTA — one encrypted file<br/>SQLCipher 4 · ~/.kepta/kepta.db")]
  A & B & C --> K --> E

⚡ Two commands — plus one bridge

npx -y kepta-mcp setup   # connects Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Gemini CLI, Cline and Roo Code
npx -y kepta-mcp ui      # your memory in the browser — watch your AI use it, live
npx -y kepta import chatgpt <export-folder>   # bring your ChatGPT history with you (export → extract → import)

Then tell your AI something worth keeping — and watch it arrive. Details in the Quick start.

🚀 KEPTA — one engine, three tiers

KEPTA is one product family around one engine. The engine in this repository is what your agents talk to — free and open source, forever. The desktop app, KEPTA Pro, is what you work in. Teams and organizations get the same app with more control on top.

Core is never crippled to sell Pro — the best memory engine we can build is the free one. What we sell is how you use it.

KEPTA Pro — the full desktop app

A native app for macOS and Windows that turns the same encrypted knowledge base into a second brain you can see, search, shape and trust — every document, every decision, every connection, on your own machine.

Shortened. The full README is on GitHub.

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

Grade history

  • 2026-09-19restoreB → Ascore 92

KEPTA — the memory for AI systems: common questions

Is KEPTA — the memory for AI systems MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the KEPTA — the memory for AI systems safety report
How do I install KEPTA — the memory for AI systems?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does KEPTA — the memory for AI systems need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is KEPTA — the memory for AI systems maintained?
The last commit was 22 days ago (2026-10-13). The latest release is v3.4.0.
What can I use instead of KEPTA — the memory for AI systems?
Servers from other publishers that do the same job: M3 Memory MCP server, DocsMint MCP server and Reverie MCP server. Compare all KEPTA — the memory for AI systems alternatives.
How does KEPTA — the memory for AI systems compare with other Web search MCP servers?
safety score 92/100 (higher than 90% of 3,470 Web search servers); tools 8 (the typical Web search server has 5); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to KEPTA — the memory for AI systems

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

All KEPTA — the memory for AI systems alternatives →
  • M3 Memory
    Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.
    A
  • DocsMint
    Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
    A
  • Reverie
    Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
    B
  • Repomix
    Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
    A
  • ThoughtDAG
    Search local AI conversations by file or phrase and recall source turns. Four read-only tools.
    A