Cortex Memory Engine runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 16 Jun 2026.
Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.
What the code does
We read the source, 15 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.
engine.record_op(crate::sync::oplog::SyncPayload::MemoryDelete { id })
{
tracing::warn!(error = %e, "failed to record privacy retraction");
execSync(`tar xzf "${tarPath}" -C "${tmpDir}"`, { stdio: "pipe" });
el.innerHTML = items.map(m => `
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.
Alternatives to Cortex Memory Engine
same job, measured the same wayLocal-first knowledge engine for AI agents: memory, graph, and recall over MCP.
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Local-first durable AI memory with policy-bound recall and a typed project graph.
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
Persistent, encrypted, deterministic memory for AI agents. Local-first, 173 canonical tools.
Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.
Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.
Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.
Cortex Memory Engine — questions
Answers built from our own checks of this server.