Architecture map
How the repo is organized
Click systems in the graph to inspect responsibilities, important files, and nearby dependencies.
Architecture map
Use this map to orient around systems, dependencies, and files worth reading first.
Click a system in the map
Explore supermemoryai/smfs by selecting services, gateways, clients, and data stores. Each node shows the files, responsibilities, and neighboring systems an agent should keep in scope.
Pan, zoom, and use the minimap to keep large repos navigable.
Sign up to turn selected graph context into repo-aware agent sessions.
Key systems
What an agent should understand first
Command dispatcher: mount, unmount, login, grep, sync, status, logs, init
POSIX filesystem trait interface, inode/dentry/file operations, MemFs in-memory implementation
Background loops: delta pull (A), deletion scan (C), push worker (D), inflight poller (E)
7 tables: fs_inode (AUTOINCREMENT), fs_dentry (parent→child), fs_data (chunks), fs_symlink, fs_config, fs_remote (doc ID mapping), push_queue (write coalescing)
Typed HTTP wrapper: validate_key, list_documents, get_document, add/update/delete, search, profile
FUSE (Linux) and NFS (macOS) kernel mount backends using fuser/nfsserve crates
Process lifecycle: fork dance, unix-socket IPC, signal handling, background loop orchestration
Remote document storage, semantic search (/v3/documents, /v3/search), processing status tracking
Evidence coverage
What this context is grounded in
Coverage
- Citations
- 7
- Findings
- 5
- Files discovered
- 133
- Architecture systems
- 12
- Architecture relationships
- 15
- Agent graph
- Agent graph entities
- 1,709
- Agent graph relationships
- 1,795