Memra

com.usememraPublished by usememra.comOfficial publisherv4.7.1Updated Oct 25, 2026

Persistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection.

VerifiedStreamable HTTPWeb executableDatabasesKnowledge & Memory

Overview

AI-generated overview

Memra is a remote, EU-hosted persistent memory server that lets an AI assistant store facts and decisions and recall them later with hybrid semantic and keyword

What you can do
Store and recall facts, decisions and patterns with hybrid semantic plus BM25 search that also matches exact identifiers and error codes, with token-budgeted recall and session-start bootstrap context. Detect contradictions at write time, supersede outdated memories and review full audit history. Track staleness signals and revision tokens for deterministic read-your-writes. Organize memories in multi-tenant namespaces with PII masking and read-only scoped keys for subagents.
When to use it
Use it when an assistant should carry knowledge across sessions or projects and you want recall that is deterministic and auditable rather than LLM-generated. It suits teams that need EU hosting and privacy controls, or that want contradictions and stale facts surfaced instead of silently overwritten.
Requirements
A remote Streamable HTTP endpoint; no local runtime needed. An API key from the provider, sent as an Authorization Bearer header, is required; a free tier is offered. A fully offline local package is also mentioned as an alternative.
Before you install
The API key is a credential sent in the Authorization header; keep it private and prefer read-only scoped keys for subagents. Stored memories are sent to and kept on the provider's EU-hosted service, so avoid writing secrets or sensitive personal data. Writes create, supersede and retire memories, so review what the assistant stores.

Installation

In SourceWeft

  1. Open Memra in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.usememra%2Fmemra/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "memra": {
      "type": "http",
      "url": "https://usememra.com/mcp"
    }
  }
}

README

Memra MCP Server

Persistent memory for AI agents — remote MCP server. EU-hosted (Helsinki), privacy-first, deterministic recall with no LLM in the hot path.

Endpoint: https://usememra.com/mcp (Streamable HTTP) · Registry: com.usememra/memra · Free tier, no credit card.

What it gives your agent

  • memra_remember / memra_recall — store facts, decisions, patterns; hybrid semantic + lexical (BM25) search that also matches exact identifiers and error codes
  • Write-time contradiction detection — storing a fact that clashes with existing knowledge returns conflicts[] so the agent can supersede the outdated one
  • Read-your-writes — every write returns a revision token; recall with wait_for_revision is deterministic
  • memra_supersede + memra_history — memories retire with full audit chains instead of going stale
  • Staleness signals — every result carries staleness_score / last_confirmed; the agent decides what to trust
  • Token-budget recall — max_tokens: 2000 returns the best memories that fit your context window
  • memra_bootstrap — priority context at session start
  • Multi-tenant namespaces, PII masking (7 EU language models), read-only scoped keys for subagents

Setup

Get an API key at usememra.com (free tier), then:

Claude Code

bash
claude mcp add --transport http memra https://usememra.com/mcp --header "Authorization: Bearer memra_live_YOUR_KEY"

Cursor / Cline / any MCP client (mcp.json)

json
{  "mcpServers": {    "memra": {      "url": "https://usememra.com/mcp",      "headers": { "Authorization": "Bearer memra_live_YOUR_KEY" }    }  }}

Fully offline alternative: pip install memra-local — same tools, SQLite + ONNX embeddings, zero cloud calls.

Docs

SDKs: pip install memra-sdk · npm install @usememra/sdk · composer require memra/sdk

Source: README.md at commit 08e7946

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v4.7.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts