local-memo
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@local-memo Save our conversation context"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
local-memo
Local-only MCP server for saving and restoring conversation context across AI agent sessions. No cloud, no accounts — just JSON files on disk.
Inspired by Upstash Memo, but fully local.
Why?
Memo is a great idea — save your conversation context, get a short ID, restore it later in a different session or agent. But there's no reason that data needs to leave your machine. This version replaces the cloud API + Redis with plain files in ~/.local-memo/.
Related MCP server: Infinite Context Keeper
Install
Claude Code
claude mcp add local-memo -- npx local-memoOr from a local clone:
claude mcp add local-memo -- node /path/to/local-memo/dist/index.jsClaude Desktop / Cursor
Add to your MCP config:
{
"mcpServers": {
"local-memo": {
"command": "npx",
"args": ["local-memo"]
}
}
}Usage
Save context
Ask your AI agent to save the current conversation context. It will call memo_set and return a short ID:
> Please save our conversation context
Context saved locally.
ID: 4tJ630XqhCV5gQelx98pu
Expires: 2025-01-30T14:38:51.278Z (1440 minutes)Restore context
In a new session, give the agent the ID:
> Restore memo 4tJ630XqhCV5gQelx98puList saved memos
> List my saved memosDelete a memo
> Delete memo 4tJ630XqhCV5gQelx98puTools
Tool | Description |
| Save structured context (goal, completed tasks, pending tasks, decisions, files, extra context). Returns an ID. |
| Restore context by ID. Returns formatted markdown. |
| List all unexpired memos with their IDs and goals. |
| Delete a memo by ID. |
Options
Flag | Default | Description |
|
| How long memos live before expiring |
|
| Storage directory |
Example with 7-day TTL:
claude mcp add local-memo -- npx local-memo --ttl-mins 10080Storage
Memos are plain JSON files in ~/.local-memo/memos/:
{
"id": "4tJ630XqhCV5gQelx98pu",
"createdAt": "2025-01-29T14:38:51.278Z",
"expiresAt": "2025-01-30T14:38:51.278Z",
"ttlMins": 1440,
"context": {
"goal": "Build a local memo system",
"completed": ["Designed schema", "Wrote MCP server"],
"pending": ["Test it"],
"decisions": ["Use filesystem instead of Redis"],
"files": ["index.ts", "package.json"],
"context": "Extra notes here"
}
}Back them up, sync them, grep them — they're just files.
License
MIT
Available Tools
4 toolsmemo_deleteA
Delete a saved memo by its ID.
Inputs: id (required).
memo_getA
Retrieve a previously saved conversation context by its ID.
Inputs: id (required).
memo_listA
List all saved memos that haven't expired yet.
Inputs: no named parameters.
memo_setA
Save the current conversation context for handoff to another session or agent. Returns a short ID for retrieval.
Inputs: goal (required), completed (required), files, context, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct operation on memos: get retrieves, list enumerates, set saves, delete removes. There is no overlap or ambiguity between them.
All tools follow the consistent pattern memo_<verb> (get, list, set, delete). The naming is uniform and predictable.
Four tools is a well-scoped count for a simple memo/context storage service. Each tool is necessary and none are redundant.
The tool surface covers the full lifecycle of memos: create (set), read (get), list, and delete. No obvious missing operations for the stated purpose.
Maintenance
Related MCP Connectors
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
Related MCP Servers
- AlicenseAqualityAmaintenanceFilesystem MCP server for AI assistants. Search, read, edit, and manage local files in directories you choose.6142,539 npm32MIT
- AlicenseBqualityDmaintenanceMCP server providing context usage estimation, conversation compaction, and durable semantic memory via local embeddings and SQLite.179 npm3MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first MCP server that persists AI coding agent memory and session context, enabling seamless resume across sessions with searchable memories and checkpoints.6 npm1MIT
- AlicenseAqualityBmaintenancePersistent project context (AGENTS.md), cross-session memory, and identity — discoverable by any MCP client.101,449 npm3MIT