Build team AI agents connected to approved knowledge sources and tools, with workspace access controls.
Best suited to
Build team AI agents connected to approved knowledge sources and tools, with workspace access controls.
Dust is a team-oriented AI agent workspace built around organizational knowledge and connected tools. It fits a group that wants an assistant to answer from its approved sources or support a bounded internal task. The first useful experiment is a small knowledge set and a few questions with answers you can check manually. Review both connector access and the agent’s instructions before expanding the workspace. A plausible answer is not evidence that permissions or source coverage are correct. Free introductory credits are limited lifetime access, while regular usage requires a paid seat.
Getting started (documentation-based; not a hands-on product test):
Example task (illustrative): Answer a fictional leave-policy question using only the approved policy document; say when the source is missing.
Check the result against your original input and the stated plan limits. Sources reviewed on 11 October 2026 are linked below.
Workspace AI agents
Connected knowledge sources
Tool-enabled assistants
Team collaboration
Workspace administration
Free seat has 500 lifetime credits; continuing regular access uses paid seat tiers.
Plan information can change. Prices and conditions are set by the provider. Information checked 2026-10-11.
Source for access detailsOne email a week with pricing and feature changes in this category. No per-tool price alerts.
By subscribing you agree to receive this email from Genius Forges and to us storing your address to send it. We may ask you to confirm by email. Every email has an unsubscribe link. See our privacy policy.
Dust is a team-oriented AI agent workspace built around organizational knowledge and connected tools. It fits a group that wants an assistant to answer from its approved sources or support a bounded internal task.
Free seat has 500 lifetime credits; continuing regular access uses paid seat tiers.
Create a small permitted knowledge collection.
Review permissions with a second role before adding more sources.
This listing is based on official documentation reviewed on 11 October 2026. The sample is illustrative; no hands-on product result is claimed.
Tell us what needs improving. No account or private output required.
Report incorrect information or a broken linkDocumentation-based review · 2026-10-11
Original editorial guidance based on official product and access documentation. Example tasks are illustrative, not observed product tests.
Open-source local guardrail that checks AI coding agent tool calls, secret reads, MCP use and package installs before they run.
Best for: HOL Guard is for developers who let agents such as Claude Code, Codex or Cursor run commands on their machine.
General AI agent for in-depth research, websites, slides and wide multi-item research, with credit-based plans from $20 a month.
Best for: Manus suits people who want to hand a multi-step task to an agent and get a finished piece of work back, such as a research summary, a website or a slide deck.
Anthropic coding agent for the terminal, IDEs and web that fixes bugs, runs tests and handles refactors, included in Claude paid plans.
Best for: Claude Code suits developers who want an agent that reads a whole codebase, makes multi-file changes and runs commands under their approval.