Remembra — AI Memory Layer runs on your own machine — the client starts it, so there is no endpoint to ping. 183 installs a week from pypi. Last commit 17 Jul 2026.
Persistent AI memory with entity resolution, temporal knowledge graph & 11 MCP tools.
What the code does
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
…" name="__codelineno-1-1" href="#__codelineno-1-1"></a>cat<span class="w"> </span>><span class="w"> </span>~/Library/LaunchAgents/com.remembra.server.plist<span class="w"> </span><span class="s"><< 'EOF'</span>
этот файл ставится пользователю, но в репозитории его нет
<li class="flex gap-2"><span class="text-gray-500">•</span><span><code class="bg-white/10 px-1.5 py-0.5 rounded text-xs">update_memory</code> — Update content without delete+recreate</span></li>
result = subprocess.run(
<script src="https://cdn.paddle.com/paddle/v2/paddle.js" onerror="console.warn('Paddle.js failed to load - checkout will use fallback')"></script>
featuresEl.innerHTML = plan.features.map(f => `<li>${f}</li>`).join('');
…tifications on memory events:</p> <pre><code>plugins:\n slack_notifier:\n enabled: true\n webhook_url: \"https://hooks.slack.com/services/YOUR/WEBHOOK\"\n events:\n - memory.created\n channel: \"#ai-memories\"\n</code></pre>"},{"location":"guides/plugins/#creati…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add remembra -- uvx remembra{
"mcpServers": {
"remembra": {
"args": [
"remembra"
],
"command": "uvx"
}
}
}[mcp_servers.remembra]
command = "uvx"
args = ["remembra"]{
"mcpServers": {
"remembra": {
"args": [
"remembra"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"remembra": {
"args": [
"remembra"
],
"command": "uvx"
}
}
}Alternatives to Remembra — AI Memory Layer
same job, measured the same wayPersistent memory for AI tools. Local-first knowledge graph with hybrid search.
Open-source bitemporal memory layer for LLM agents — knowledge graph with conflict resolution.
Persistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
Memori MCP server — persistent AI memory with recall and augmentation tools
Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Remembra — AI Memory Layer — questions
Answers built from our own checks of this server.