Visual Memory MCP vs Local RAG (shinpr)

Two MCP servers from our AI & ML ranking, compared on live data - updated nightly, never sponsored.

Bottom line · 2026-09-18

monthly package install counts are comparable (21,590 vs 14,904); both are actively maintained, with commits inside the last month.

How they differ in kind

Visual Memory MCP focuses on: @putervision/vision-memory-mcp is a zero-infrastructure, local-first Model Context Protocol (MCP) server and CLI tool that provides AI coding assistants (such as Cursor, Claude Code, Gemini, or… Local RAG (shinpr) focuses on: Search private documents from an MCP client or the terminal without sending them to an embedding API. Environment-variable extraction: Visual Memory MCP yielded no variables extracted; Local RAG (shinpr) yielded 3 variables.

What each one does

Visual Memory MCP

@putervision/vision-memory-mcp is a zero-infrastructure, local-first Model Context Protocol (MCP) server and CLI tool that provides AI coding assistants (such as Cursor, Claude Code, Gemini, or Copilot) with visual state caching using perceptual hashing, local CLIP embeddings, and transition graphs to eliminate repetitive vision LLM calls.

From the project's README.

Local RAG (shinpr)

Search private documents from an MCP client or the terminal without sending them to an embedding API. It runs locally over stdio via the published package.

From the project's README.

14 signals, side by side

Signal Visual Memory MCP Local RAG (shinpr)
Monthly installs 21,590 14,904
GitHub stars 70 398
Last commit 2026-09-15 2026-09-18
Releases · last 90 days 3 10+
In the registry since Jul 2026 Oct 2025
Registry versions 11 52
Documented tools not extracted - see README not extracted - see README
Env vars extracted none extracted - see README 3
Runs local (stdio) local (stdio)
Endpoint auth local only local only
Maintenance actively maintained actively maintained
License NOASSERTION MIT
Language TypeScript TypeScript
Category rank #3 of 106 #2 of 106

Environment variables found in the READMEs

These are extracted names, not a requiredness check. Project docs may mark them optional or require other setup.

Visual Memory MCP

No environment variables were extracted from the README setup. Check the project documentation for other authentication or configuration steps.

Local RAG (shinpr)

  • BASE_DIR
  • RAG_HYBRID_WEIGHT
  • BASE_DIRS

Which one, for what

Derived from the signals above, not hands-on testing.

Pick Visual Memory MCP if…

  • → measured package adoption matters - 21,590 monthly installs
  • → category standing - #3 of 106 maintained AI & ML servers

Pick Local RAG (shinpr) if…

  • → release velocity matters - 10+ releases in 90 days vs 3
  • → clear licensing matters - MIT vs undeclared

Who's behind them

Visual Memory MCP - putervision: 6 MCP servers tracked, 6 maintained, 210 combined stars. Full record.

Local RAG (shinpr) - shinpr: 3 MCP servers tracked, 3 maintained, 662 combined stars. Full record.

Not sold on either?

The next-ranked AI & ML servers we track:

Quick answers

Is Visual Memory MCP better than Local RAG (shinpr)?

The numbers don't separate them: 21,590 vs 14,904 monthly installs, and both committed within the last month. Choose on fit - execution model, extracted environment variables, endpoint authentication, and license are in the table above. Data as of 2026-09-18.

Can I use Visual Memory MCP and Local RAG (shinpr) together?

Yes - MCP clients accept multiple servers in one config, so you can enable both AI & ML servers side by side. If their tools overlap, keep the one whose toolset fits to keep your agent's tool list lean.

What environment variables do their READMEs document?

Visual Memory MCP: no environment variables extracted from the README setup; Local RAG (shinpr): 3 environment variables extracted from the README setup. Extraction does not rule out other authentication or configuration steps; check each project's current documentation.

Keep exploring: best AI & ML servers · TypeScript servers · all comparisons · every server

Methodology: package-usage signal = npm/PyPI installs (last month, platform APIs) · maintenance = commit recency + release cadence (GitHub) · tool lists and environment-variable names extracted from each project's README · endpoint auth from our own nightly probes. We haven't hand-tested these servers; everything here is data as of 2026-09-18.