Home / Directory / Agents & orchestration / Agent platforms & frameworks / Dust
Dust
Multiplayer enterprise AI workspace for building, sharing, and governing human-agent collaboration with company knowledge and tools.
Operations, support, and GTM teams that want governed, multiplayer agents connected to Slack, Notion, Drive, and similar sources.
Engineering groups that only need an open-source agent framework they fully own, or buyers who refuse seat-plus-credit packaging.
Co-founded by Gabriel Hubert.
Verdict
Dust is a good fit when the job is a shared agent workspace with connectors, permissions, and multi-model choice rather than a raw Python framework. Teams like the no-code agent builder and company-context depth; expect to budget Pro and Max seats carefully once agents run tool-heavy workflows. It is a conditional recommend until credit burn on your real agents is proven.
Score Breakdown
How Dust scores in the categories that matter to its buyers.
Pricing
Dust publishes a Business plan with credit-metered seat types, plus Enterprise by quote. Figures below are from dust.tt/home/pricing as of September 2026 (EUR list). Credits meter model tokens and tool actions; unused monthly credits do not roll over.
| Seat / plan | Meter | Price | What stands out |
|---|---|---|---|
| Free (Business seat) | Seat | EUR 0 | 500 credits lifetime; occasional users |
| Pro (Business seat) | Per seat / mo | EUR 30 (or EUR 24 / mo yearly) | 8,000 credits / seat / mo |
| Max (Business seat) | Per seat / mo | EUR 150 (or EUR 120 / mo yearly) | 40,000 credits / seat / mo; tool-heavy agents |
| Programmatic / API | Per credit | $0.01 | Business rate; Enterprise custom |
| Enterprise | Workspace | Sales quote | Pooled credits, SCIM, audit logs, single-tenant |
The Field at a Glance
Where Dust ranks among Agent platforms & frameworks vendors we reviewed, by Overall Score and relative typical engagement cost.
Dust falls between open frameworks and packaged agent suites: higher product polish than raw CrewAI crews, lower engineer-framework depth than LangChain. Overall Score is 6.8. Relative typical engagement cost lands in the mid band once Pro and Max seats stack.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Shared company agents for ops/support | Strong | Core multiplayer workspace strength. |
| Connector-backed knowledge Q&A | Strong | Broad SaaS connectors and permissions. |
| Code-first multi-agent systems | Mixed | Engineers may still prefer LangChain or CrewAI. |
| Air-gapped custom framework ownership | Weak | Managed workspace first; Enterprise single-tenant still vendor-run. |
Review Excerpts
Below are excerpts from public reviews. Paid reviews and pay-for-play sites such as Clutch were excluded.
“Dust has become as critical to our teams as web search. Unified search across Notion, Google Drive, Slack, Gong, and Salesforce in a single query changed how we brief accounts.”
“Custom agents that understand internal terminology cut repetitive onboarding questions roughly 40% for our new hires.”
“Initial indexing on a large documentation estate took days, and per-seat credits add up once every team spins agents.”
“UI still feels rough around the edges for non-English teams; we wanted better localization before a global rollout.”
“We deploy department agents for competitive intel, Zendesk macros, and codebase search, then share the same agent definitions instead of siloed ChatGPT chats.”
Methodology
This page is an independent evaluation of Dust for buyers comparing options in agent platforms & frameworks. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Dust did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria fall under it in two groups.
- Buyer outcomes (for agent platforms & frameworks)
- Shared agent workspace
- Company knowledge connectors
- Governance & permissions
- Framework depth for engineers
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Dust is graded here as agent platforms & frameworks. Criteria scores can move as more review volume and product checks are added.