agentic-recall runs on your own machine — the client starts it, so there is no endpoint to ping. 120 installs a week from npm.
Long-term memory for agentic tasks. It tells you when it doesn't know.
Today is the operative word: we check agentic-recall every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 agentic-recall -- npx -y agentic-recall
{
"mcpServers": {
"agentic-recall": {
"args": [
"-y",
"agentic-recall"
],
"command": "npx"
}
}
}
[mcp_servers.agentic-recall]
command = "npx"
args = ["-y", "agentic-recall"]
{
"mcpServers": {
"agentic-recall": {
"args": [
"-y",
"agentic-recall"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentic-recall": {
"args": [
"-y",
"agentic-recall"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
MEMORY_DIR (Absolute path to the folder holding your markdown memories. Required — the server never searches your disk for it.), MEMORY_ROOT (Optional. Where the embedding model cache, vector cache and indexes are kept. Defaults beside the code for a clone, ~/.agentic-recall for a package install.).
The author declared them in the registry entry; get the values from the project itself.
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
Your AI's memory for what you actually know: recall across your documents, notes, and meetings
Persistent memory layer for AI coding agents — your agent remembers what you taught it.
Local-first, governable long-term memory for AI coding agents
Git-backed long-term memory authority for AI agents via MCP.
Answers built from our own checks of this server.