Project Structure

After running swarmvault init, your workspace looks like this:

my-vault/
|-- swarmvault.config.json
|-- swarmvault.schema.md
|-- inbox/
|-- raw/
|   |-- sources/
|   `-- assets/
|-- wiki/
|   |-- index.md
|   |-- sources/
|   |-- concepts/
|   |-- entities/
|   `-- outputs/
|-- state/
|   |-- manifests/
|   |-- extracts/
|   |-- analyses/
|   |-- graph.json
|   |-- search.sqlite
|   |-- compile-state.json
|   `-- jobs.ndjson
`-- agent/

Key Directories

  • **swarmvault.schema.md** - vault-specific markdown instructions used by compile and query
  • **inbox/** - staging area for browser clips, imported markdown bundles, and other capture workflows
  • **raw/sources/** - immutable canonical copies of ingested source files
  • **raw/assets/** - copied sidecar assets referenced by ingested markdown bundles
  • **wiki/** - generated markdown pages for sources, concepts, entities, indexes, and saved outputs
  • **state/manifests/** - source metadata, content hashes, storage locations, and attachment references
  • **state/extracts/** - extracted text used during analysis
  • **state/analyses/** - provider-generated analysis output
  • **state/jobs.ndjson** - automation run log written by swarmvault watch
  • **agent/** - agent-specific files and future agent integrations

Main Artifacts

  • **state/graph.json** - compiled graph data
  • **state/search.sqlite** - local full-text search index
  • **wiki/index.md** - entry point into the compiled markdown wiki

Configuration File

swarmvault.config.json controls workspace paths, provider configuration, task routing, viewer settings, and installed agent types. swarmvault.schema.md controls vault-specific naming, categorization, and grounding behavior. See Configuration and Schema for details.