Providers

SwarmVault uses a capability-driven provider abstraction that supports multiple LLM backends through a unified interface.

Supported Providers

TypeDescriptionRequires API Key
heuristicLocal fallback using term frequency and regexNo
openaiOpenAI API (GPT-4o, etc.)Yes
anthropicAnthropic API (Claude)Yes
geminiGoogle Gemini APIYes
ollamaLocal Ollama instanceNo
openrouterOpenRouter preset over the OpenAI-compatible adapterYes
groqGroq preset over the OpenAI-compatible adapterYes
togetherTogether preset over the OpenAI-compatible adapterYes
xaixAI preset over the OpenAI-compatible adapterYes
cerebrasCerebras preset over the OpenAI-compatible adapterYes
openai-compatibleAny OpenAI-compatible APIVaries
customLoad from a custom moduleVaries

Provider Capabilities

Each provider declares its capabilities:

  • responses — OpenAI Responses API format
  • chat — Chat completions format
  • structured — Structured/JSON output
  • tools — Tool/function calling
  • vision — Image understanding
  • embeddings — Text embeddings
  • streaming — Streaming responses
  • local — Runs locally without network

Privacy & Data Flow

SwarmVault keeps the default data path local:

  • Code files are parsed on your machine via tree-sitter and are not sent to external APIs
  • Documents and text are sent only to the provider you configure for semantic extraction
  • Images are sent only when you configure a vision-capable provider
  • The built-in heuristic provider stays fully offline and requires no API keys

Adding a model provider changes the semantic extraction path for non-code content, but graph building, community detection, and report generation still happen locally.

Provider Interface

All providers implement:

  • generateText(request) — Generate plain text
  • generateStructured(request, schema) — Generate validated structured output

See individual provider pages for configuration details.