Engram runs on your own machine — the client starts it, so there is no endpoint to ping. 249 installs a week from npm. Last commit 22 Sep 2026.
Cognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams.
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.
postinstall: node scripts/preflight.cjs
self._proc = subprocess.Popen(
execFile(cmd, args, { encoding: "utf8", windowsHide: true, maxBuffer: 16 * 1024 * 1024, cwd: opts.cwd, env: opts.env ?? process.env, timeout: opts.timeoutMs }, (err, stdout, stderr) => {
env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 engram -- npx -y @devinmlowe/engram
{
"mcpServers": {
"engram": {
"args": [
"-y",
"@devinmlowe/engram"
],
"command": "npx"
}
}
}
[mcp_servers.engram]
command = "npx"
args = ["-y", "@devinmlowe/engram"]
{
"mcpServers": {
"engram": {
"args": [
"-y",
"@devinmlowe/engram"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"engram": {
"args": [
"-y",
"@devinmlowe/engram"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ENGRAM_DB_PATH (SQLite database path (default: <data dir>/engram.db, i.e. ~/.local/share/engram/engram.db)), ENGRAM_MCP_PORT (Port of the optional engram HTTP daemon to bridge to (default 9907)), ENGRAM_MCP_TOKEN (Bearer token forwarded to the HTTP daemon when it requires one), ENGRAM_MCP_STANDALONE (Set to 1 to never bridge: always run the full server in-process).
The author declared them in the registry entry; get the values from the project itself.
Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
Persistent knowledge graph for AI agents. Remember, recall, and forget facts.
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.
Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
Answers built from our own checks of this server.