@memofs/mcp-server
OfficialSupports Cloudflare R2 for blob storage and Workers AI for graph extraction within the memory store.
Can be deployed on Cloudflare Workers, with an adapter for Workers AI-powered entity extraction.
Connector plugin that ingests content from GitHub repositories/issues into the memory store.
Connector plugin that ingests content from Notion into the memory store for recall.
Allows fully local vector search via onnxruntime, running embeddings in-process without external API keys.
Provides an embeddings adapter for semantic search, enabling vector-based recall within the memory system.
Uses Turso/libSQL as a metadata store for the memory system.
Integrates with Vercel AI SDK to provide runtime bridges and tool definitions for AI agents.
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 checkpointsRelated MCP server: contextforge-mcp
Quick Start
Reach first success in under a minute. No API keys, no database setup, no cloud required.
npm install @memofs/coreimport { 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 CloudThe 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
unverifiedstatus.Semantic GC — archive deprecated memories to cold storage; restore on demand via
memofs restore.Session outcomes —
success/failure/abortedoutcome oncomplete()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 |
Core runtime, virtual AgentFS, graph engine, and hybrid recall router. | |
CLI tool for local and cloud memory workflows ( | |
Self-hostable, OSS-deployable memory server for Node and Workers. | |
Model Context Protocol server exposing memory tools to AI agents. | |
Local ingestion framework plugins (Notion, GitHub). | |
Message schemas and validation for JSON-RPC 2.0. |
Providers & Adapters
Package | Purpose |
Vercel AI SDK integration, runtime bridges, and tool definitions. | |
OpenAI embeddings adapter. | |
Voyage AI embedder and reranker adapter. | |
ONNX local embedder (Transformers.js) for zero-API-key hybrid recall. | |
Cloudflare Workers AI graph extractor adapter. | |
Cloudflare R2 Blob storage adapter. | |
Turso / libSQL metadata store adapter. |
Development Tooling
Package | Purpose |
Shared contract tests, mocks, fakes, and fixtures. | |
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 |
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.jsonWorkspace 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:buildContributing
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.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
An MCP memory server. One memory your agents share — across models, devices and apps.
- mcpOAuthai.butlerbrain
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Related MCP Servers
- AlicenseCqualityDmaintenanceMCP server for sharing source-backed engineering memory across AI coding clients like Cursor and VS Code.301MIT
- AlicenseBqualityCmaintenancePersistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based, Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based organization, and team collaboration via Model Context Protocol.691,1102MIT
- AlicenseNot gradedqualityAmaintenanceOpen-source MCP memory server providing persistent, cross-platform context for AI tools via a knowledge graph with encrypted storage.413AGPL 3.0
- FlicenseNot gradedqualityDmaintenanceA persistent, conflict-aware memory MCP server for AI coding assistants (Cursor, Claude Code).-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/memo-fs/memofs'
If you have feedback or need assistance with the MCP directory API, please join our Discord server