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.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles Dust the way a machine reads it — 57 machine-readable artifacts across 14 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Dust scores 76.0/100 (exemplar), with a separate agent-readiness read of 48/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
How we profile Dust
Each block below is one kind of artifact we hold for Dust. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 14
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Dust Agents API
Agent configurations
Dust Apps API
Dust apps
Dust Conversations API
Conversations
Dust Datasources API
Data sources
Dust DatasourceViews API
Data source views
Dust Feedbacks API
Message feedbacks
Dust MCP API
MCP servers
Dust Mentions API
Mentions
Dust Search API
Search
Dust Skills API
Skills
Dust Spaces API
Spaces
Dust Tools API
Tools
Dust Triggers API
Triggers
Dust Workspace API
Workspace
Scroll within the panel for all 14 ·
Postman Collections 9
A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.
Ready-to-run Postman collections for exercising this provider's APIs.
Dust Agents API
POSTMANDust Apps API
POSTMANDust Conversations API
POSTMANDust Data Sources API
POSTMANDust MCP API
POSTMANDust Search API
POSTMANDust Skills API
POSTMANDust Triggers API
POSTMANDust Workspace API
POSTMANScroll within the panel for all 9 ·
Open Collections 9
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
Dust Agents API
OPEN COLLECTIONDust Apps API
OPEN COLLECTIONDust Conversations API
OPEN COLLECTIONDust Data Sources API
OPEN COLLECTIONDust MCP API
OPEN COLLECTIONDust Search API
OPEN COLLECTIONDust Skills API
OPEN COLLECTIONDust Triggers API
OPEN COLLECTIONDust Workspace API
OPEN COLLECTIONScroll within the panel for all 9 ·
Arazzo Workflows 12
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
Dust Approve a Pending Agent Tool Action
Start a conversation, wait for the agent to request a tool action, then approve or reject it.
ARAZZODust 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.
ARAZZODust Converse with an Agent
Start a conversation, mention an agent, and poll the conversation until the agent answers.
ARAZZODust Create a Table and Upsert Rows
Upsert a structured table into a data source, then load rows into it and read one back.
ARAZZODust Discover Spaces and Data Sources
List the workspace's accessible spaces, then enumerate the data sources within a chosen space.
ARAZZODust Find Agent and Start a Conversation
Search for an agent by name, resolve its full configuration, then open a conversation mentioning it.
ARAZZODust Import an Agent and Start a Conversation
Create a new agent configuration from a JSON definition, then open a conversation that mentions it.
ARAZZODust Message an Agent and Submit Feedback
Post a message into a conversation, wait for the agent reply, then submit thumbs feedback on it.
ARAZZODust Post Follow-up Message and Poll
Post a follow-up message into an existing conversation and poll the conversation for the agent reply.
ARAZZODust Run an App and Poll for Completion
Trigger a non-blocking Dust app run and poll the run until its status succeeds or errors.
ARAZZODust Suggest a Mention and Start a Conversation
Resolve a mention query into an agent suggestion, then open a conversation that mentions it.
ARAZZODust 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.
ARAZZOScroll within the panel for all 12 ·
Pricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Dust Plans Pricing
PLANSRate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Dust Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Dust Finops
FINOPSSemantic Vocabularies 1
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Dust Context
JSON-LDSpectral Rules 1
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
Dust API Rules
SPECTRALJSON Schema 5
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
Dust Agent Configuration
JSON SCHEMADust Conversation
JSON SCHEMADust Data Source
JSON SCHEMADust Document
JSON SCHEMADust Skill
JSON SCHEMASecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for Dust — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 10
Portal, sign-up, and the first successful call
Scroll within the panel for all 10 ·
Documentation 3
Reference material describing how the API behaves
Agent Surfaces 1
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 12
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 12 ·
Build 14
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 14 ·
Access & Security 5
Authentication, authorization, and security posture
Learn 1
Tutorials, courses, talks, and written guidance
Operate 5
Status, limits, changes, and where to get help
Commercial 6
Pricing, plans, and the legal terms of use
Company 3
The organization behind the API
← All providers · Data indexed from github.com/api-evangelist/dust-tt · machine-readable index on apis.io