Memento

A local-first, LLM-agnostic memory layer for AI assistants — runmemento.com

Every AI session starts the same way: re-explaining your preferences, your project's conventions, the decisions you made last week, the dead-ends to avoid. Each tool solves this in its own siloed way (CLAUDE.md, .cursorrules, copilot-instructions.md, ChatGPT Memory) — but you, the human, are the one constant. Your memory shouldn't fragment across vendors.

Memento is one place where that memory lives. It runs an MCP server over a local SQLite file, so any MCP-capable AI assistant — Claude Desktop, Claude Code, Cursor, GitHub Copilot, Cline, OpenCode, Aider, a research bot, a custom agent — can read and write durable, structured memory about you, your work, and your decisions. Local-first, no outbound network calls by default, no vendor lock-in.

Quickstart

Three steps from zero to a working memory layer:

1. Initialize Memento

npx @psraghuveer/memento init

Creates the database under the XDG default ($XDG_DATA_HOME/memento/memento.db, typically ~/.local/share/memento/memento.db on POSIX), runs migrations, and prints copy-paste MCP snippets for every supported client. Idempotent — re-run any time to reprint the snippets.

2. Connect your AI client

init prints, for each client, either a one-line subcommand (e.g. claude mcp add memento … for Claude Code) or a JSON snippet to merge into the client's MCP config (Claude Desktop, Cursor, Cline, VS Code Agent mode, OpenCode). Pick the one for your client, paste it, then restart the client so it loads the new MCP server.

The full per-client walkthrough lives in docs/guides/mcp-client-setup.md.

3. Teach your assistant when to use Memento

Memento exposes the MCP tools, but the assistant still needs to know when to call them. Two paths, depending on your client:

• If your client loads Anthropic-format skills: install the bundled Memento skill. One cp -R command, printed by init, copies it into ~/.claude/skills/ — the path most skill-capable clients read from. (A few use a client-specific directory; check your client's docs and re-target the cp if the skill doesn't pick up after a restart.) Restart the client; the skill auto-loads on intent match.

• If your client doesn't support skills: paste the persona snippet from docs/guides/teach-your-assistant.md into your client's persona file (.cursorrules, custom system prompt, etc.).

That's it. Verify with npx @psraghuveer/memento doctor --mcp (scans known client configs and flags shape mismatches) and try a fresh session: "Remember that I prefer pnpm over npm for Node projects." In the next session, ask "What's my preferred package manager?" and the assistant should recall it without you re-explaining.

Seed your store with a pack

A fresh Memento install is empty. Packs are curated YAML bundles of memories you can install in one step — a stack guide (Rust + Axum, TypeScript + pnpm, Python + uv…), a team's conventions, or a personal set you authored on another machine.

memento pack install engineering-simplicity

That command installs one of the bundled packs — eleven memories distilled from John Maeda's The Laws of Simplicity. Four bundled packs ship out of the box: engineering-simplicity, pragmatic-programmer (Hunt & Thomas's tips), twelve-factor-app (Wiggins / Heroku), and google-sre (Google's SRE books). Preview before installing with memento pack preview <id-or-path>; list what's installed with memento pack list; remove any time with memento pack uninstall <id> --confirm (dry-run by default).

Packs are also how you share. Author one from your existing memories with memento pack create, then distribute it as a file, an HTTPS URL, or a community contribution. The reserved pack:<id>:<version> tag stamps every pack-installed memory so provenance never drifts. Full guide: docs/guides/packs.md. Design rationale: ADR-0020.

Getting started

Prerequisites. Node.js ≥ 22.11, and a C/C++ toolchain so better-sqlite3 can compile on platforms without a prebuild (Xcode command-line tools on macOS, build-essential on Debian/Ubuntu).

Run init once to set things up:

npx @psraghuveer/memento init

init defaults the database to the XDG data dir; pass --db /custom/path/memento.db (or set MEMENTO_DB=/custom/path/memento.db) if you want a non-default location.

To run the server directly (e.g. for debugging):

npx @psraghuveer/memento serve

The server listens on stdio for MCP requests. To pass extra flags (e.g. a custom database location):

npx @psraghuveer/memento serve --db ~/.local/share/memento/memento.db

You can also point at an existing database with the MEMENTO_DB environment variable.

Verify the install by running npx @psraghuveer/memento doctor (add --quick to skip the DB and embedder probes; add --mcp to also scan known MCP client config files). For a one-screen summary of what's in your store, npx @psraghuveer/memento status. To inspect what your install can do — registered commands, current config, database location — without speaking MCP, run npx @psraghuveer/memento context. To smoke-test the MCP transport end-to-end, npx @psraghuveer/memento ping.

Wiring Memento into an MCP client (Claude Desktop, Claude Code, Cursor, Cline, OpenCode, VS Code Agent mode, …) is covered step by step in docs/guides/mcp-client-setup.md. The TL;DR is the three-step quickstart above: init, paste the snippet, install the skill or paste the persona.

Vector retrieval (paraphrase matching on top of FTS) is on by default. The first search triggers a one-time model download (~110 MB) into $XDG_CACHE_HOME/memento/models (or ~/.cache/memento/models / %LOCALAPPDATA%\memento\Cache\models); after that, both FTS and vector arms run automatically. If the model has not yet downloaded, search degrades gracefully to FTS-only. For configuration options and library-wiring details, see docs/guides/embeddings.md.

Operating the store day-to-day — compact, backup, status, scheduling — is covered in docs/guides/operations.md. The conflict workflow is in docs/guides/conflicts.md. To prime an AI assistant on how to use Memento well, see docs/guides/teach-your-assistant.md — or, if your client supports Anthropic skills (Claude Code, Cowork), install the bundled skill for a no-config alternative.

See and curate your store in a browser. npx @psraghuveer/memento dashboard launches a local-first web UI that reads against your MEMENTO_DB: memory counts by kind and scope, audit trail, conflict triage, config inspection, installed packs. Localhost-only, gated by a per-launch random token in the URL the launcher hands the browser, no telemetry. The dashboard is a sibling package (@psraghuveer/memento-dashboard) shipped under ADR-0018; see docs/guides/dashboard.md for the full walkthrough.

Stuck? Common failure modes (better-sqlite3 build errors, command not found: memento, STORAGE_ERRORs, missing embedder dependency) are covered in docs/guides/troubleshooting.md.

For the contributor workflow (branching, commit conventions, PR checklist) see CONTRIBUTING.md. AI agents working on the codebase must also read AGENTS.md.

Guiding principles

These are the four principles every design decision is judged against. They are documented at length in ARCHITECTURE.md.

1. First principles. Every construct exists because we proved we need it, not because it's how things are usually done.

2. Modular. Any component can be replaced without rewriting the rest.

3. Extensible. New variants don't require breaking changes.

4. Config-driven by the user. Behavior is shaped by configuration, not by code.

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).

What Memento is not

• Not a chat history store. It records distilled, structured memory — preferences, facts, episodes, lessons — not raw transcripts.

• Not a knowledge graph or semantic database. Use the right tools for that.

• Not a cloud service. Memory lives on your machine; cloud embedders, sync across machines, and team-shared memory are not part of the product.

• Not a plugin platform. The architecture leaves the door open, but Memento ships with a fixed surface to hold the line on quality.

The full list of out-of-scope and current limitations is in KNOWN_LIMITATIONS.md.

How it fits together

┌─────────────────────────────────────────────────────────┐
│  Clients: Claude Desktop, Claude Code, Cursor, Copilot, │
│           OpenCode, custom agents, …                    │
└──────────────────────┬──────────────────────────────────┘
                       │ MCP (stdio)
┌──────────────────────▼──────────────────────────────────┐
│  memento-server (MCP adapter)                           │
└──────────────────────┬──────────────────────────────────┘
                       │ Command registry
┌──────────────────────▼──────────────────────────────────┐
│  memento-core: services, scope resolver, scrubber,      │
│                conflict detector, decay engine          │
└──────────────────────┬──────────────────────────────────┘
                       │ Repository interfaces
┌──────────────────────▼──────────────────────────────────┐
│  SQLite (better-sqlite3) + FTS5 + optional sqlite-vec   │
└─────────────────────────────────────────────────────────┘

A full architectural walkthrough lives in ARCHITECTURE.md. Each significant decision has an Architecture Decision Record.

For contributors (human or AI)

Contributions are welcome from both human and AI-assisted authors. We treat them with the same standards.

• Read AGENTS.md if you are an AI agent or working with one. It is the canonical instruction set; CLAUDE.md and .github/copilot-instructions.md are thin pointers to it.

• Read CONTRIBUTING.md for development setup, branching, commit conventions, and the PR lifecycle.

• Open a design proposal issue before any non-trivial change.

• Use the PR template. It asks you to justify, not just describe, the change.

We use GitHub Discussions for questions and ideas; the issue tracker is for bugs and accepted work.

License

Apache-2.0. See NOTICE for attribution.

Packages

Memento is a small workspace of focused packages. The architecture is documented in docs/architecture/ and the design decisions in docs/adr/; both are the source of truth for what Memento does and why.