MemoFS MCP Server

MemoFS

Open-source, file-first memory runtime for AI agents.

---

What is MemoFS?

File-first memory runtime for AI agents. Store, recall, and synchronize memory using plain files on disk — local-first by default, with optional cloud sync.

Most AI memory systems are database-first, vendor-locked, hard to inspect, and hard to version. MemoFS inverts that: your agent's memory lives as Markdown and JSONL under a .memofs/ directory you can cat, git diff, and roll back.

.memofs/
├── config.json       # Workspace settings and engine routing
├── manifest.json     # Asset registry tracking and hashes
├── memory/
│   ├── core.md       # Durable, project-wide facts (Markdown)
│   └── notes.md      # Timestamped notes and logs (Markdown)
├── events/
│   └── conversations.jsonl # Chronological interactions for recall
├── graph/
│   ├── nodes.jsonl   # Entities extracted from memory
│   └── edges.jsonl   # Relational connections
├── archive/          # Cold storage for deprecated memories
│   └── <id>.json     # Full-fidelity archived memory records
└── snapshots/
    └── snap_123.json # Versioned restore checkpoints

---

Quick Start

Reach first success in under a minute. No API keys, no database setup, no cloud required.

npm install @memofs/core

import { MemoFS } from "@memofs/core";
import { createNodeFsMemoryStore } from "@memofs/core/node-fs";

// Initialize a Node.js filesystem-backed memory store
const store = createNodeFsMemoryStore({
  rootDir: ".",
});

// Create the unified client
const memo = new MemoFS({
  store,
  projectId: "my-app",
  mode: "local",
});

// Read project-wide core memory (core.md)
const core = await memo.core.read();
console.log(core);

// Record a durable note (notes.md)
await memo.notes.record({
  content: "User prefers TypeScript with ESM modules.",
  kind: "preference",
});

// Recall works offline (lexical BM25 + fuzzy matching) with zero config
const hits = await memo.recall("TypeScript configuration");

To upgrade to semantic/vector search, plug in an embedder adapter like OpenAI (@memofs/adapter-openai) or Voyage AI (@memofs/adapter-voyage). For zero-API-key local vector search, enable the ONNX embedder (@memofs/adapter-transformers) to run embeddings completely in-process.

To connect your coding agent (Cursor, Claude Code, etc.), use the stdio-compatible @memofs/mcp-server.

---

Architecture

Your App / Agent / MCP client
        │
        ▼
    MemoFS   (local-first runtime)
      ├─ .read() / .write() / .recall()
      ├─ .snapshot.create() / .restore()
      ├─ AgentFS  (lease-locking & virtual paths)
      └─ .sync *  (Cloud sync pushes and pulls)

   read() / write() / recall() — core client methods
        │
        ▼
   .memofs/   (plain files on disk)
     ├─ memory/core.md      ├─ memory/notes.md
     ├─ events/*.jsonl      ├─ graph/{nodes,edges}.jsonl
     └─ snapshots/  manifest.json
        │   git-friendly, inspectable, versionable
        ▼   (optional)
   MemoFS Cloud

The runtime resolves configuration from constructor options → env vars → .memofs/config.json. Three runtime modes are supported: local (filesystem-only, default), hybrid (local + cloud sync with read/write policies), and memory (in-memory volatile, ideal for tests).

Memory Intelligence

• Code anchoring & drift detection — bind memories to source files; stale memories are rank-demoted at recall time when anchored code changes.
• Memory decay floors — kind-specific expiry thresholds (30–365 days) transition old memories to unverified status.
• Semantic GC — archive deprecated memories to cold storage; restore on demand via memofs restore.
• Session outcomes — success / failure / aborted outcome on complete() governing durable memory promotion and workspace cleanup.

---

Packages

MemoFS is structured as a monorepo containing 15 published public packages under the @memofs/ scope. The CLI ships as @memofs/cli and installs the memofs command.

Core Engine & Servers

Package	Purpose
@memofs/core	Core runtime, virtual AgentFS, graph engine, and hybrid recall router.
@memofs/cli	CLI tool for local and cloud memory workflows (npx memofs).
@memofs/server	Self-hostable, OSS-deployable memory server for Node and Workers.
@memofs/mcp-server	Model Context Protocol server exposing memory tools to AI agents.
@memofs/connectors	Local ingestion framework plugins (Notion, GitHub).
@memofs/json-rpc	Message schemas and validation for JSON-RPC 2.0.

Providers & Adapters

Package	Purpose
@memofs/adapter-ai-sdk	Vercel AI SDK integration, runtime bridges, and tool definitions.
@memofs/adapter-openai	OpenAI embeddings adapter.
@memofs/adapter-voyage	Voyage AI embedder and reranker adapter.
@memofs/adapter-transformers	ONNX local embedder (Transformers.js) for zero-API-key hybrid recall.
@memofs/adapter-workers-ai	Cloudflare Workers AI graph extractor adapter.
@memofs/adapter-r2	Cloudflare R2 Blob storage adapter.
@memofs/adapter-turso	Turso / libSQL metadata store adapter.

Development Tooling

Package	Purpose
@memofs/testing	Shared contract tests, mocks, fakes, and fixtures.
@memofs/benchmark-kit	Benchmark workloads and runners.

---

Open Source vs. MemoFS Cloud

The core runtime is open source (MIT) and fully functional locally. You do not need a cloud account to run MemoFS.

MemoFS Cloud is the memory plane for your agents: it keeps every machine, teammate, and agent on the same memory, and gives you a dashboard to see and govern it.

Feature	Open source (this repo)	MemoFS Cloud
Local file-first memory	✅	✅
CLI + stdio MCP server	✅	✅
All adapters (OpenAI, Voyage, etc.)	✅	✅
Hosted sync (keep memory in sync)	✅ client	✅ hosted
Team workspaces & access control	—	✅ available
Memory dashboard (explore, consolidate)	—	✅ available
Hosted managed MCP endpoint	—	✅ available (Pro+)
Managed runtime (memory API over HTTPS)	—	Soon

Join the Cloud waitlist →

---

Repository Structure

memofs/
├── apps/
│   └── docs/         # VitePress documentation (docs.memofs.dev)
├── packages/         # 15 published @memofs/* packages
├── tooling/          # Private @repo/* workspace build packages
├── benchmarks/       # Workspace benchmarking suite
├── examples/         # Runnable examples
└── package.json

---

Workspace Commands

Run these command tasks from the repository root:

# Install all dependencies
pnpm install

# Build all packages and applications
pnpm build

# Run TypeScript compilation checks
pnpm typecheck

# Run unit tests across all packages
pnpm test

# Run code style checks (Biome)
pnpm format-and-lint

# Fix linting and formatting issues automatically
pnpm format-and-lint:fix

# Build documentation locally
pnpm docs:build

---

Contributing

See CONTRIBUTING.md for details on formatting, testing, and pull requests. For roadmap targets, see ROADMAP.md.

For security reports, refer to SECURITY.md — do not open public issues for security vulnerabilities.

---

License

MIT. See LICENSE.