Skip to content
SPECIFICTION
Get listed

Dust vs SEPIA

Dust

dust.tt

SEPIA

sepia-framework.github.io

Side by side

FigureDustSEPIA
Price from€24/mo—
Free planYes—
Free trial——
Open source——
WebYesYes
Windows—Yes
macOS—Yes
Linux—Yes
iOS—Yes
Android—Yes
APIYes—
Self-hosted—Yes
Plans published60
Spec score · AI Agent Builders8.4 (#6)6.7 (#29)
SupportDust offers email support, a help agent, and a community, and says it responds to support requests within two business days.The documentation directs users with questions or bug reports to GitHub issues or discussions.

Plans

Dust

  • FreeFree
  • Pro€24 a month
  • Max€120 a month
  • Pro€288 a year
  • Max€1,440 a year
  • EnterprisePriced on request

Dust pricing →

SEPIA

No plans published.

SEPIA pricing →

In their own words

Dust

Dust connects company knowledge, tools, and teams so organizations can build, share, and run AI agents across workflows. People and agents coordinate through shared knowledge, tools, conversations, notifications, and human review. Dust lists 70+ connectors, including Slack, Notion, Google Drive, GitHub, Salesforce, and Zendesk, and supports building agents with more than 20 frontier and open-source models from providers such as OpenAI, Anthropic, Google, and Mistral. Agents can run multi-agent workflows on schedules and triggers, with reusable skills, tools, and memory. Its Chrome extension provides access to company knowledge and AI assistance from the current tab. Dust says it is SOC 2 Type II certified and GDPR compliant, and enables HIPAA compliance. Its Free plan includes 500 credits for lifetime use. Pro costs €24 a month billed yearly, and Max costs €120 a month billed yearly. Enterprise is listed without a price and includes unlimited connectors and MCP servers, workspace-pooled credits, SCIM, audit logs, single-tenant deployment, and priority support with an SLA.

Visit dust.tt

SEPIA

SEPIA is an open-source framework and cross-platform app for building a customizable digital voice assistant with a self-hosted server. The server runs core functions such as the database, account management, natural-language understanding and chat. Users can make commands in the app, build voice-controlled services with the Java SDK or replace framework modules. SEPIA accepts spoken or typed requests and can ask follow-up questions when a service needs more detail. Documented services include news, radio, timers, alarms, reminders, to-do and shopping lists, smart home, navigation, weather, Wikipedia and web search. The documentation names openHAB as a smart-home integration, and SEPIA-Home v2.7.0 release notes add Home Assistant support. Speech recognition can use native platform APIs or a custom open-source STT server; text-to-speech can use native APIs or compatible server tools. Client use is described for desktop browsers, Android and iOS; iOS instructions use Safari and adding the app as a PWA. Server guidance covers Windows, Mac, Linux and Raspberry Pi. SEPIA says users control their data in a self-hosted environment, but it does not currently host public servers, so users need access to their own server or one provided by someone else.

Visit sepia-framework.github.io