Dust
Platform for team agents on company knowledge
Dust is a platform where teams build, share and use their own AI agents on several LLMs, invoked in conversations via @ mentions. Agents access company knowledge through connectors such as Slack, Notion, Google Drive, GitHub or Salesforce. With the run_agent tool, an agent calls another agent as a tool, either in the background with the result returned or as a complete handoff to the specialized agent, up to a recursion depth of 4. Dust targets companies that want to embed agents in the daily work of many employees. Billing is per user with credits. The source code is on GitHub under the MIT license, but Dust is only offered as a hosted service (SaaS); self-hosting is not supported.
Good fit if
Focus: Teams and companies using agents on internal knowledge broadly in daily work
- your project is about Knowledge search across company data, Support and sales agents or Delegation to specialized agents
- people without programming skills should work with it (4/5 for use without developers)
- your team is just getting started (skill level: Beginner to Intermediate)
- you want to get started quickly (learning curve: flat)
Key figures
- Usable without developers
- 4/5
- Scalability
- 4/5
- Integrations
- 4/5
- Versioning
- 2/5
- Observability
- 3/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Enterprise
- Type
- Platform for team agents on company knowledge
- Licence
- MIT (Quellcode), Nutzung als SaaS
- Pricing
- Freemium / EnterpriseBusiness Free €0 (500 lifetime credits). Business Pro €24 per user/month billed yearly, €30 billed monthly (8,000 credits/month). Business Max €120 or €150 per user/month (40,000 credits). Enterprise on request; prices excl. VAT.
- Deployment
- Cloud
- Models
- OpenAI, Anthropic, Google, Mistral, DeepSeek
- Compliance
- SOC 2, GDPR
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO yes, RBAC yes
- GitHub stars
- 1,500
Key features
- run_agent: agent as a tool or handoff to specialized agents
- 70+ connectors to company knowledge
- 20+ models from various providers
- Spaces with access permissions
- Data hosting in the EU or US
Typical use cases
- Knowledge search across company data
- Support and sales agents
- Delegation to specialized agents
- Automating internal processes
Market notes
Changes to Dust by email
We let you know when the status, pricing or license of Dust changes, together with the weekly market notes.
Implementation
Get Dust implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- EnterpriseLangdockLangdock is an enterprise AI platform offering chat, agents, workflows and knowledge bases on models from several providers. Subagents let you attach one agent to another; the parent agent delegates tasks during a conversation, and each subagent runs with its own instructions, knowledge, actions and model. Delegation is limited to one level, and users need access to every subagent. Langdock targets organizations rolling out AI broadly to employees, with hosting in the EU. Billing is per user per month, with enterprise on request.View profile
- EnterpriseGlean AgentsGlean is an enterprise search and assistant platform that indexes content from more than 250 enterprise applications while respecting permissions. In the Agent Builder, agents are built as a flow of steps; a step can call a sub-agent that returns its outputs to the parent agent. Through the A2A host, Auto mode agents can also use external agents as subagents via the Agent2Agent protocol. Glean targets large enterprises; pricing is available on request only.View profile
- EnterpriseAgentforce (Salesforce)Agentforce is Salesforce's agent platform that companies use to build and run AI agents for customers and employees. The agents use data, workflows and permissions from Salesforce and Data Cloud and can be customized with low-code or pro-code tools. Guardrails, testing and monitoring are built in.View profile
- EnterpriseOracle AI Agent StudioOracle AI Agent Studio is the environment where Oracle customers and partners create and customize agents and agentic workflows for Oracle Fusion Cloud Applications such as ERP, HCM and SCM. Workflows include Multi Agent nodes in which a supervisor agent routes requests to specialized worker agents and returns a consolidated response for requests spanning several topics. According to Oracle, the studio supports MCP and A2A agent cards as well as models from several providers. Oracle states that AI Agent Studio is available to Fusion customers at no additional cost; Custom AI is a separate offering.View profile