Remembra - AI Memory Layer MCP Server

The memory layer for AI that actually works. Persistent memory with entity resolution, temporal decay, and graph-aware recall. It runs locally over stdio via the published package.

People connecting memory tools to Claude, Cursor, VS Code, or another MCP client. The project is written in HTML.

VERIFIED ACTIVE

LAST COMMIT 2026-07-17 · ★ 15 · #157 OF 259 MAINTAINED MEMORY · VERIFIED 2026-08-25

MIT · HTML · how we verify → /methodology

01 · Install Remembra - AI Memory Layer

before you install - you'll need

Set REMEMBRA_URL before connecting. REMEMBRA_USER_ID is optional or environment-specific per the README.

Claude Code

claude mcp add remembra-ai-remembra -- uvx remembra

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "remembra-ai-remembra": {
      "command": "uvx",
      "args": [
        "remembra"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package remembra - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.remembra-ai is GitHub-verified and matches the repo owner

03 · What Remembra - AI Memory Layer can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.13.2 · 2026-04-25

v0.13.1 · 2026-03-30

v0.13.0 · 2026-03-27

What's New in v0.13.0 · Dashboard v2.0 · Two-Factor Authentication - TOTP-based 2FA with any authenticator app · Team Collaboration - Shared memory spaces with Viewer/Member/Admin roles · Admin Dashboard - Full user…

04 · Who maintains Remembra - AI Memory Layer

Remembra - AI Memory Layer is maintained by remembra-ai. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/remembra-ai/remembra
website: https://remembra.dev/
category: memory - ranked #157 of 259 actively-maintained memory servers as of 2026-08-25.
registry: io.github.remembra-ai/remembra (active, first published 2026-03-02 · 4 versions)
packages: pypi:remembra

06 · Remembra - AI Memory Layer FAQ

What is Remembra - AI Memory Layer?

The memory layer for AI that actually works. Persistent memory with entity resolution, temporal decay, and graph-aware recall. It runs locally over stdio via the published package.

Is Remembra - AI Memory Layer still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-17. We re-verify nightly.

How do I install Remembra - AI Memory Layer?

Run `uvx remembra`. The README documents 2 environment variables (REMEMBRA_URL, REMEMBRA_USER_ID) to set first. Set REMEMBRA_URL before connecting. REMEMBRA_USER_ID is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Remembra - AI Memory Layer run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Remembra - AI Memory Layer

Alternatives to Remembra - AI Memory Layer

Maintained memory servers if Remembra - AI Memory Layer isn't the fit.

Pairs well with

Servers that cover what Remembra - AI Memory Layer doesn't - only shown when the pairing reason fits the companion.

More memory MCP servers · Replen · WingmanProtocol Agent Gateway · Zettel Forge · Memory OS AI