Persistent AI Memory MCP Server

by savantskie• 236•• Scanned•Claim this listing•Request removal
Database Managementai assistantembeddingsgithub copilotlmstudiomcp server

A persistent local memory for AI, LLMs, or Copilot in VS Code.

Persistent AI Memory is an open-source mcp server by savantskie, written mainly in Python, with 236 GitHub stars and the MIT license. Its code was last updated Sep 20, 2026.

Scan summary: scanned Nov 5, 2026 at commit 2364c45. Seen able to run dynamic code. Scan policy

What Persistent AI Memory can touch

  • Run shell commandsNot seen in this scan
  • Run dynamic codeFound in the code by our scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsNot seen in this scan
  • Control a web browserNot seen in this scan
  • Connect to databasesLikely, from its own description
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNot run in this scan

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 2364c45, Nov 5, 2026. See the scan policy.

Before you install Persistent AI Memory

AgenticMart scanned Persistent AI Memory on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An MCP server is a program your AI app starts and talks to. A local one runs with your user's permissions: it can see the files, environment variables and network your account can.
  • Based on its description and topics, it likely needs to connect to a database.
  • Based on its description and topics, it likely needs to use a code-hosting token (GitHub/GitLab).

Before you install

  1. Give it a read-only database user unless it must write.
  2. Use a fine-grained token limited to the repos it needs.
  3. Pin the version you reviewed instead of always installing the latest release.
  4. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by savantskie on GitHub, 236 stars and 30 forks. Popularity is not proof of safety.
  • Last code change: Sep 20, 2026.
  • Open-source license: MIT.

Persistent AI Memory is an open-source mcp server by savantskie, written mainly in Python. A persistent local memory for AI, LLMs, or Copilot in VS Code.

At a glance

Stars
236
Forks
30
Language
Python
License
MIT
Created
Aug 2025
Last update
Sep 20, 2026
Type
MCP Server
Price
Free

Topics

ai-assistantembeddingsgithub-copilotlmstudiomcp-serverollamapersistent-memorysemantic-searchsqlite

Questions about Persistent AI Memory

What is Persistent AI Memory?

A persistent local memory for AI, LLMs, or Copilot in VS Code.

Who maintains Persistent AI Memory?

Persistent AI Memory is maintained by savantskie on GitHub (savantskie/persistent-ai-memory). AgenticMart lists it from public repository data.

Is Persistent AI Memory safe to use?

AgenticMart scanned Persistent AI Memory on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does Persistent AI Memory use?

It is published under the MIT license.

Persistent AI Memory alternatives

View more →

Similar mcp servers in Database Management, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Persistent AI Memory (this page)
savantskie
236MITSep 20, 2026Scanned, no flagged issues
Codebase Memory MCP
DeusData
48kMITNov 1, 2026Scanned, see report
Xerj
xerj-org
19kApache-2.0Nov 1, 2026Scanned, no flagged issues
MCP Toolbox
googleapis
17kApache-2.0Nov 1, 2026Scanned, no flagged issues
Nightingale
ccfos
13kApache-2.0Oct 30, 2026Scanned, no flagged issues
Dbhub
bytebase
3.8kMITOct 26, 2026Scanned, no flagged issues