Skip to content

Settings Reference

To get started with settings, see Connect a Cloud Provider. For background on provider trade-offs, see The Provider Spectrum.

Daneel’s settings are organized into 19 panels, accessible via the gear icon on the launcher bubble.

Dashboard overview showing:

  • Active LLM provider and model
  • GPU/hardware summary (GPU name, cores, RAM, VRAM, bandwidth)
  • Index statistics (indexed sites, total chunks, storage estimate)
  • Appearance summary (theme, color, position)
  • Privacy and telemetry status
  • License plan and feature flags
  • MCP server count
  • Current page index status

Latest updates, features, and release notes from the Daneel AI team.

ControlOptionsDefault
ThemeLight, DarkSystem-detected
Color styleDefault (slate), Cyan, Magenta, Yellow, Green, NeonDefault
Launcher positionBottom right, Bottom centerBottom right
ControlDescription
ExportDownload a .zip of all settings, vaults, indexes, agents, MCP configs
ImportRestore from a .zip backup (drag-drop or file picker)
Azure Blob StorageSAS URL input for cloud backup
S3-Compatible StorageAccess key, secret, bucket, region, endpoint for S3/R2/B2/MinIO

See How to Back Up Your Data for step-by-step instructions.

Cross-provider model browser with:

  • Search — filter by name, provider, description
  • Provider filter — All, WebGPU, Ollama, Claude, Azure, Gemini Nano
  • Privacy filter — On-device only, Local network, Your cloud, Any cloud
  • Capability filter — Tool calling, Thinking, Vision
  • Hardware detection — GPU description, VRAM, RAM, GFLOPS, shader-f16 support
  • Model wizard — guided recommendation based on your hardware
  • Expandable model cards — description, quality rating, match score, license, effective context window, speed estimate, data residency
ControlDescription
Model selectionChoose from 20+ models auto-filtered by GPU compatibility
Model loadingDownload and cache models for offline use
StatusCurrent model status, GPU detection results
ControlDescription
Base URLOllama server address (default: http://localhost:11434)
Model selectionDropdown of installed models (auto-detected)
Model managementPull new models, delete existing ones
Connection statusAuto-probe indicator
ControlDescription
AvailabilityAuto-detected Chrome AI API status
LanguageLanguage preference for the built-in model
ControlDescription
API keyEncrypted input (AES-256-GCM, stored locally)
Model selectionOpus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5
ControlDescription
Endpoint URLAzure OpenAI resource endpoint
Deployment nameYour model deployment name
Auth methodAPI Key or Entra ID (OAuth2)
API keyInput field (when API Key auth is selected)

See How to Set Up Azure OpenAI.

ControlDescription
Indexed sites listDomain, page count, chunk count, last indexed date
Re-indexRe-crawl and update a site’s index
ClearDelete all indexed data for a domain

Default crawl parameters:

ParameterDefault
Max pages150
Max depth3
Max chunks per page2,000
Chunk size512 tokens
Chunk overlap64 tokens

See How to Manage Site Indexes.

ControlDefaultDescription
NER modelGLiNER Small v2.1 int8Entity extraction model (4 options, 183–583 MB)
Ontology presetGeneralEntity type categories (8 presets + custom)
Custom ontologyUser-defined entity type labels
Dedup threshold0.85Entity name similarity threshold for merging
Extraction threshold0.55Minimum confidence for entity extraction
Max entity width12Maximum token span for a single entity
Particle animationOnAnimated particles on graph edges
Bloom glowOffGlow effect on nodes
Particle speed0.004Animation speed
Charge strength-80Node repulsion force
Node scale4Base node size multiplier
Link opacity0.4Edge transparency
Background color#060810Visualization background
Bloom strength1.0Intensity of bloom effect

See How to Build a Knowledge Graph.

ControlDescription
Featured serversCurated list of known-good MCP servers
SearchBrowse MCP registries
Registered serversYour connected servers with status badges
Add custom serverSSE URL + auth configuration
Enable/disableToggle individual servers without removing them
Test connectionVerify server responds

See How to Connect an MCP Server.

ControlDescription
Agent listAll configured agents
Create/edit agentName, purpose, system prompt, bound MCP servers
DeleteRemove an agent

See How to Create a Custom Agent.

ControlDescription
Companion sidecarAlways included (port 8809)
Ollama presetToggle Ollama container (port 11434)
MCP server templatesAdd from catalog or custom command
YAML previewLive preview of the generated compose file
ExportDownload daneel.compose.yml + auto-register servers

See How to Set Up the Docker Companion.

Hardware and runtime information: GPU details, browser version, extension version, memory usage.

ControlDefaultDescription
Share location with agentsOffInject city-level geolocation into agent system prompts. Triggers a browser permission prompt on first enable.
Share date & timezone with agentsOnInject current date, time, and IANA timezone into prompts. No permission needed.

These are global gates — when off, no agent or MCP server can trigger context injection regardless of its own flags. See Environment Context for the full architecture.

ControlDefaultDescription
Anonymous usage analyticsOnFeature usage telemetry via GA4
Enhanced geolocationOffIP-based country/region for analytics (separate from agent context injection)

Collected: feature usage counters (chat, search, crawl, model load, MCP, agents, vault), provider and model name, OS, Chrome version, language, country/region.

Never collected: page content, URLs visited, chat messages, personal information.

See Privacy Model for the full data flow explanation.

ControlDescription
StatusCurrent plan and feature flags
UnlockOpens Stripe checkout
Enter keyManual license key entry (DAN-XXXX-XXXX-XXXX)

Diagnostic tools: logs, storage inspection, runtime state.