Dust

Dust is a Paris-based enterprise AI platform for building, deploying, and operating teams of AI agents that have shared context across a company's knowledge and tools. Dust positions itself as the platform for "AI Operators" — the people who design, govern, and continuously improve agentic workflows across Sales, Customer Support, Marketing, Engineering, Data & Analytics, IT, Legal, Recruiting, and Knowledge teams. Agents in Dust are model-agnostic (OpenAI, Anthropic, Google, Mistral), grounded on company data through 100+ connectors (Slack, Notion, GitHub, Google Drive, Salesforce, Zendesk, Jira, Confluence, HubSpot, BigQuery, Snowflake), exposed via a REST API, MCP servers (client- and server-side), webhooks, and OAuth2, and reachable from a multiplayer conversation UI, Slack, a Chrome extension, a Raycast extension, and a CLI. The Dust core platform is open source under the MIT license at github.com/dust-tt/dust. The hosted service is available on a per-seat Pro plan (29 EUR / user / month) and a custom Enterprise tier (100+ seats) with SSO, SCIM, dedicated environments, EU residency, and SOC 2 Type II / GDPR / HIPAA-ready compliance.

9 APIs 0 Features

AgentsAIArtificial IntelligenceCustom WorkflowsData SourcesDustEnterprise AIKnowledge ManagementLLMMCPMulti-ModelRAG

APIs

Dust Agents API

Create, list, retrieve, update, archive, search, import, and export Dust agent configurations. An agent in Dust is a named, versioned configuration of an LLM (OpenAI, Anthropic,...

Dust Conversations API

Drive multi-turn conversations with Dust agents. Create conversations, post user messages, stream agent events over SSE, attach content fragments (file/page/snippet attachments)...

Dust Data Sources API

Manage Dust data sources, data source views, spaces, documents, tables, and folders. Upsert documents and table rows programmatically, search semantically, manage hierarchies an...

Dust MCP API

Register a client-side Model Context Protocol server with a Dust workspace, stream MCP tool-call requests over SSE, return tool execution results back to Dust agents, and keep t...

Dust Apps API

List Dust Apps in a space and create or retrieve App runs. Dust Apps are chained-block LLM/code pipelines defined in the Dust Builder and executable as parameterized "functions"...

Dust Search API

Search nodes (documents, tables, folders, conversations) across an entire Dust workspace. Streaming SSE variant for incremental result delivery, plus a tool-file upload endpoint...

Dust Skills API

List the skill bundles installed in a Dust workspace and import new skills from uploaded files. Skills are reusable instruction + tool packs that agents can attach to.

Dust Triggers API

Receive an external webhook on a registered Dust webhook source and fan it out to trigger agent workflows (e.g. run an agent when a GitHub issue opens or a Notion page changes).

Dust Workspace API

Export workspace analytics and pull aggregated workspace usage data for chargeback, capacity planning, and FinOps reporting against Dust seat and programmatic-API consumption.

Collections

Dust Agents API

POSTMAN

Dust Apps API

POSTMAN

Dust Conversations API

POSTMAN

Dust Data Sources API

POSTMAN

Dust MCP API

POSTMAN

Dust Search API

POSTMAN

Dust Skills API

POSTMAN

Dust Triggers API

POSTMAN

Dust Workspace API

POSTMAN

Dust Agents API

OPEN

Dust Apps API

OPEN

Dust Conversations API

OPEN

Dust Data Sources API

OPEN

Dust MCP API

OPEN

Dust Search API

OPEN

Dust Skills API

OPEN

Dust Triggers API

OPEN

Dust Workspace API

OPEN

Arazzo Workflows

Dust Approve a Pending Agent Tool Action

Start a conversation, wait for the agent to request a tool action, then approve or reject it.

ARAZZO

Dust Attach a File and Ask an Agent

Reserve a file upload URL, attach the file as a content fragment, then ask an agent about it.

ARAZZO

Dust Converse with an Agent

Start a conversation, mention an agent, and poll the conversation until the agent answers.

ARAZZO

Dust Create a Table and Upsert Rows

Upsert a structured table into a data source, then load rows into it and read one back.

ARAZZO

Dust Discover Spaces and Data Sources

List the workspace's accessible spaces, then enumerate the data sources within a chosen space.

ARAZZO

Dust Find Agent and Start a Conversation

Search for an agent by name, resolve its full configuration, then open a conversation mentioning it.

ARAZZO

Dust Import an Agent and Start a Conversation

Create a new agent configuration from a JSON definition, then open a conversation that mentions it.

ARAZZO

Dust Message an Agent and Submit Feedback

Post a message into a conversation, wait for the agent reply, then submit thumbs feedback on it.

ARAZZO

Dust Post Follow-up Message and Poll

Post a follow-up message into an existing conversation and poll the conversation for the agent reply.

ARAZZO

Dust Run an App and Poll for Completion

Trigger a non-blocking Dust app run and poll the run until its status succeeds or errors.

ARAZZO

Dust Suggest a Mention and Start a Conversation

Resolve a mention query into an agent suggestion, then open a conversation that mentions it.

ARAZZO

Dust Upsert a Document and Search the Data Source

Upsert a document into a data source, wait for the upsert queue to drain, then search for it.

ARAZZO

Pricing Plans

Dust Plans Pricing

2 plans

PLANS

Rate Limits

Dust Rate Limits

4 limits

RATE LIMITS

FinOps

Dust Finops

FINOPS

Semantic Vocabularies

Dust Context

17 classes · 17 properties

JSON-LD

Resources

PostmanWorkspace

PostmanWorkspace

Documentation

APIReference

GettingStarted

GettingStarted

GitHubOrganization

GitHubOrganization

ContactSales

TrustCenter

TermsOfService

PrivacyPolicy

BrowserExtension

BrowserExtension

AcademyMode

Sources

opencollection: 1.0.0
info:
  name: Dust Workspace API
  version: 1.0.2
items:
- info:
    name: Workspace
    type: folder
  items:
  - info:
      name: Export Workspace Analytics
      type: http
    http:
      method: GET
      url: https://dust.tt/api/v1/w/:wId/analytics/export
      params:
      - name: wId
        value: ''
        type: path
        description: Unique string identifier for the workspace
      - name: table
        value: ''
        type: query
        description: 'The analytics table to export:

          - "usage_metrics": Messages, conversations, and active users over time.

          - "active_users": Daily, weekly, and monthly active user counts.

          - "source": Message volume by context origin (web, slack, etc.).

          - "agents": Top agents by message count.

          - "users": Top users by message count.

          - "skill_usage": Skill executions and unique users over time.

          - "tool_usage": Tool executions and unique users over time.

          - "messages": Detailed message-level logs.

          '
      - name: startDate
        value: ''
        type: query
        description: Start date in YYYY-MM-DD format
      - name: endDate
        value: ''
        type: query
        description: End date in YYYY-MM-DD format
      - name: timezone
        value: ''
        type: query
        description: IANA timezone name (defaults to UTC)
      - name: format
        value: ''
        type: query
        description: Output format (defaults to csv)
      auth:
        type: bearer
        token: '{{bearerToken}}'
    docs: Export analytics data for the workspace identified by {wId} in CSV or JSON format.
  - info:
      name: Get Workspace Usage Data
      type: http
    http:
      method: GET
      url: https://dust.tt/api/v1/w/:wId/workspace-usage
      params:
      - name: wId
        value: ''
        type: path
        description: Unique string identifier for the workspace
      - name: start
        value: ''
        type: query
        description: The start date in YYYY-MM or YYYY-MM-DD format
      - name: end
        value: ''
        type: query
        description: The end date in YYYY-MM or YYYY-MM-DD format (required when mode is 'range')
      - name: mode
        value: ''
        type: query
        description: The mode of date range selection
      - name: format
        value: ''
        type: query
        description: The output format of the data (defaults to 'csv')
      - name: table
        value: ''
        type: query
        description: 'The name of the usage table to retrieve:

          - "users": The list of users categorized by their activity level.

          - "assistant_messages": The list of messages sent by users including the mentioned agents.

          - "builders": The list of builders categorized by their activity level.

          - "assistants": The list of workspace agents and their corresponding usage.

          - "feedback": The list of feedback given by users on the agent messages.

          - "all": A concatenation of all the above tables.

          '
      - name: includeInactive
        value: ''
        type: query
        description: Include users and assistants with zero messages in the export (defaults to false)
      auth:
        type: bearer
        token: '{{bearerToken}}'
    docs: 'Deprecated: this endpoint will be removed after 2026-06-01.

      Use GET /api/v1/w/{wId}/analytics/export instead.


      Get usage data for the workspace identified by {wId} in CSV or JSON format.

      '
bundled: true