Memento

by veerps57

381 downloads
Not rated
GitHub

About

Memento is a local-first, LLM-agnostic memory layer. It runs an MCP server over a single SQLite file on your machine, so any MCP-capable AI assistant — Claude Desktop, Claude Code, Cursor, GitHub Copilot, Cline, OpenCode, Aider, a custom agent — can read and write durable, struct

Details

Author
veerps57
Downloads
381
Categories
AI, Knowledge Base

- Five typed memory kinds: fact, preference, decision, todo, snippet
- Vector retrieval with FTS (first‑time model download ~110 MB)
- Bundled skills and persona snippets for assistant instruction
- Curated memory packs for seeding conventions and guides
- Local‑only dashboard web UI (npx @psraghuveer/memento dashboard)

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Memento
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install and initialize with npx @psraghuveer/memento init, which creates the database, runs migrations, and offers interactive setup. Then paste the printed MCP snippet into your AI client’s configuration and restart the client. After that, ensure the persona snippet reaches the assistant (auto-installed for many file-based clients; manual pasting for UI‑only clients). Verify setup with npx @psraghuveer/memento verify-setup. You can also run the server directly with npx @psraghuveer/memento serve.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "memento": {
            "memento": {
                "command": "npx",
                "args": [
                    "-y",
                    "@psraghuveer/memento",
                    "serve"
                ]
            }
        }
    }
}

McpServers

{
    "memento": {
        "command": "npx",
        "args": [
            "-y",
            "@psraghuveer/memento",
            "serve"
        ]
    }
}

What Memento is

Four pillars. Same four words used everywhere else this is described.

- Local. One SQLite file under your home directory. No cloud, no telemetry, no outbound network calls by default. Fully offline.
- Typed. Five memory kinds — fact, preference, decision, todo, snippet — with kind-specific fields (a decision carries its rationale, a todo its due date, a snippet its language). The assistant can reason about what's still true, not just retrieve text blobs.
- Audited. Every write produces an event in an append-only log. Conflicts surface for triage instead of silently coexisting. Memories decay if you don't confirm them. You can answer "why is this here?" and "when did it change?" at any time.
- Yours. Configurable behavior (every retrieval weight, every decay half-life, every scrubber rule), JSONL export and import, Apache-2.0. Carry your memory between machines, leave any time. No vendor lock-in.

Plus: LLM-agnostic (works with whatever model your client talks to), MCP-native (Claude Desktop, Claude Code, Cursor, GitHub Copilot, Cline, OpenCode, Aider, custom agents), privacy-conscious (regex scrubber strips secrets before persistence; patterns are user-configurable).

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.