# Docs


- **Getting Started**
- [Quick Start](/docs): Get up and running with MemoFS — the file-first memory runtime for AI agents.
- [What is MemoFS?](/docs/introduction): The file-first memory runtime for AI agents — architecture, mental model, and agent memory loop.

- **Runtime & Protocols**
- Core Runtime
  - [@memofs/core](/docs/core): Core architecture, subpath exports, runtime boundaries, and memory primitives of the @memofs/core package.
  - [Core Concepts](/docs/core/concepts): Architecture of canonical files, durability tiers, secret safety, code anchoring, memory decay, and knowledge graphs in MemoFS.
  - [Configuration](/docs/core/configuration): Configuration options, precedence resolution, filesystem options, and environment variables for MemoFS instances.
  - [Reading & Writing Memory](/docs/core/memory): Core memory operations, classified memory writes, notes, conversation logging, and document helpers in @memofs/core.
  - [Recall & Prompt Context](/docs/core/recall): Hybrid lexical and semantic retrieval, progressive context disclosure, and the 4-stage strategist pipeline in @memofs/core.
  - [Knowledge Graph Engine](/docs/core/graph): Entity-relationship modeling, graph extraction, traversal, pathfinding, and memory consolidation in @memofs/core.
  - [Snapshots & Rollback](/docs/core/snapshots): Memory checkpoints, atomic state restoration, and disaster recovery in @memofs/core.
  - [Agents Virtual Filesystem](/docs/core/agentfs): Virtual file-system abstraction (AgentFS) providing safe read/write boundaries for AI agents.
  - [Cloud Replication (Hybrid Mode)](/docs/core/sync): Two-phase push and pull synchronization protocols for mirroring local memory with MemoFS Cloud.
  - [Utilities & Helper Functions](/docs/core/utilities): Validation, maintenance, cryptographic helpers, path guards, chunking, and testing utilities in @memofs/core.
  - [MemoFS Client Reference](/docs/core/reference): Complete API reference for the MemoFS unified client class, instance properties, and sub-namespace methods.
- MCP Server
  - [Model Context Protocol Server](/docs/mcp): Model Context Protocol (MCP) server package for exposing MemoFS memory tools to AI agents.
  - [Hybrid Mode](/docs/mcp/hybrid-mode): Hybrid MCP operation mode combining local disk storage with cloud replica synchronization.
  - [Hosted MCP Endpoint](/docs/mcp/hosted-mcp-endpoint): Connecting AI agents to remote MemoFS Cloud Hosted MCP servers over HTTPS with SSE/Streamable HTTP.
- CLI
  - [Command Line Interface](/docs/cli): Command-line interface (@memofs/cli) reference for initializing, syncing, and managing agent memory.
  - [Memory Commands](/docs/cli/memory): CLI commands for reading, recording, searching, and consolidating project memory.
  - [Agent Commands](/docs/cli/agent): CLI commands for managing AgentFS-backed AI agent sessions and working memory.
  - [Generate Commands](/docs/cli/generate): CLI commands for scaffolding agent rules, IDE configurations, and MCP client setups.
  - [Connectors Commands](/docs/cli/connectors): CLI commands for configuring and running data ingestion connectors (GitHub, Notion).
  - [Cloud Commands](/docs/cli/cloud): CLI commands for authenticating, verifying health, and syncing file replicas with MemoFS Cloud.
  - [Config Commands](/docs/cli/config): CLI commands for inspecting and initializing local .memofs/ configuration files.
- Adapters
  - [Adapters Overview](/docs/adapters): Overview of storage and intelligence provider adapters for MemoFS: OpenAI, Voyage, Transformers.js, Cloudflare Workers AI, R2, Turso, and Vercel AI SDK.
  - [OpenAI Adapter](/docs/adapters/openai): OpenAI embeddings adapter for MemoFS vector search and semantic recall.
  - [Voyage AI Adapter](/docs/adapters/voyage): Voyage AI embeddings and neural reranking adapter for high-precision code and document recall in MemoFS.
  - [Transformers.js Adapter](/docs/adapters/transformers): Local Hugging Face Transformers.js ONNX embedding adapter for 100% offline semantic recall in MemoFS.
  - [Cloudflare Workers AI Adapter](/docs/adapters/workers-ai): Cloudflare Workers AI graph extractor adapter for serverless edge inference in MemoFS.
  - [Cloudflare R2 Adapter](/docs/adapters/r2): Cloudflare R2 blob storage adapter for MemoFS remote-blob memory stores.
  - [Turso / libSQL Adapter](/docs/adapters/turso): Turso / libSQL metadata manifest adapter for MemoFS remote-blob memory stores.
  - [Vercel AI SDK Adapter](/docs/adapters/ai-sdk): Vercel AI SDK adapter for MemoFS runtime bridging, tool definitions, and memory context builders.
- Connectors
  - [Connectors Framework](/docs/connectors): Provider-neutral data ingestion framework for synchronizing external data sources into MemoFS memory.
  - [Built-in Connectors](/docs/connectors/built-in-connectors): Technical reference guide for built-in GitHub and Notion connectors in MemoFS.
  - [Writing Custom Connectors](/docs/connectors/custom-connectors): Step-by-step guide to authoring, testing, and registering custom data ingestion connectors in MemoFS.

- **Self-Hosting & Cloud**
- Self-Hosting
  - [Server Deployment](/docs/server): Self-hosted HTTP/JSON-RPC server package for running MemoFS in centralized Node.js or Cloudflare Workers environments.
  - [Node.js Server](/docs/server/node): Deploying @memofs/server on Node.js with the memofs-server CLI, custom node:http servers, Express, or Fastify.
  - [Cloudflare Workers](/docs/server/cloudflare): Deploying @memofs/server on Cloudflare Workers using R2, Turso/libSQL, Workers AI, and Service Bindings.
  - [HTTP API (JSON-RPC 2.0)](/docs/server/http-api): JSON-RPC 2.0 protocol specifications, endpoint routing, live vs gated methods, and error formats for @memofs/server.
  - [Configure Storage](/docs/server/storage): Configure filesystem, in-memory, Turso libSQL, Cloudflare R2, and remote S3-compatible blob storage backends for MemoFS.
  - [Configure Intelligence](/docs/server/intelligence): Configure semantic embeddings, vector stores, graph consolidation, and LLM reranking models for MemoFS.
  - [API Reference](/docs/server/api-reference): Complete API reference for @memofs/server functions, options, dispatch handlers, and protocol constants.

- **Developer Tooling**
- Developer Tooling
  - [JSON-RPC Primitives](/docs/tooling/json-rpc): Zero-dependency JSON-RPC 2.0 protocol primitives, request validation, error envelopes, and spec codes for MemoFS.
  - [Testing Framework](/docs/tooling/testing): Shared contract tests, in-memory fakes, fixtures, and Vitest presets for MemoFS packages and custom adapters.
  - [Benchmark Kit](/docs/tooling/benchmark-kit): Benchmarking framework, statistical analysis, preset workload factories, and markdown reporters for MemoFS.

- **Reference**
- API Reference
  - [API Reference Overview](/docs/api): Complete API reference for MemoFS npm packages: @memofs/core, @memofs/server, @memofs/mcp-server, and @memofs/connectors.
  - [@memofs/core API Reference](/docs/api/core): Comprehensive technical API reference for @memofs/core, @memofs/core/node-fs, and @memofs/core/cloud-client.
  - [@memofs/cli API Reference](/docs/api/cli): Comprehensive technical API reference for @memofs/cli: runner, config writers, error hierarchy, protocol constants, and output formatters.
  - [@memofs/server API Reference](/docs/api/server): Complete TypeScript API reference for @memofs/server: runtime assembly, HTTP core, Cloudflare Worker handler, and JSON-RPC dispatch.
  - [@memofs/mcp-server API Reference](/docs/api/mcp-server): Comprehensive technical API reference for @memofs/mcp-server and @memofs/mcp-server/http: protocol servers, transports, runtime adapters, and SDK integration.
  - [@memofs/connectors API](/docs/api/connectors): API reference for @memofs/connectors: ingestion pipelines, connector registry, deterministic note ID generation, and third-party sources.