Tailscale vs Dust
Side-by-side trajectory, velocity, and editorial themes.
Tailscale fills out enterprise plumbing while opening a new front in AI-agent control.
The mainline Tailscale client and Terraform provider continue to ship steadily — v1.98 with MagicDNS and Linux subnet-router fixes, Terraform v0.29 adding first-class Tailscale Services support. Admin-console work (domain management, device posture visibility, paid-tier scaling for tagged resources) targets enterprise operability. Underneath the routine version cadence, the recent Aperture beta points the company up the stack into AI-agent governance.
Two threads are running in parallel. The connectivity product is hardening for larger deployments: Terraform-native service modeling, posture surfacing in the console, and explicit billing levers for tagged resources past the 50-device line. The second thread, Aperture, repositions Tailscale's identity-and-policy primitives as a control plane for LLM calls and agent tools — same trust model, new target workload.
Expect Aperture to graduate out of beta with broader provider coverage and tighter ties to Tailscale ACLs, while the core client continues a predictable point-release cadence. The enterprise plumbing improvements suggest paid-tier expansion (more usage-based dials) before the next big platform push.
Dust is widening the agent-platform surface: multimodal tools, enterprise audit, model breadth.
Dust is shipping at a fast clip on three fronts that together define a serious agent platform: model breadth (Gemini 3.5 Flash, Grok 4.3, refreshed Anthropic lineup), agent capability (MCP tools can now return images the agent can actually see, plus context compaction for long runs), and enterprise readiness (workspace audit logs streamable to Datadog, Splunk, or any HTTPS sink). Integrations are getting versioned upgrades on the side (Asana MCP v2, Gmail labels and archive). The product is moving from 'chat with an agent' toward 'run agents in production with observability and multimodal I/O.'
Two clear directions: deeper enterprise GTM via SIEM-grade audit, and a more capable agent runtime that can see, remember, and act inside third-party SaaS. The MCP-image release in particular treats Model Context Protocol as a real I/O surface rather than a text-only RPC, which is where the broader MCP ecosystem is heading. Frequent model rotations suggest Dust is positioning as model-agnostic infrastructure rather than locking into one provider.
Next moves likely lean into the same arc: more MCP integrations with action verbs (write/delete/transition states), expanded multimodal returns (audio, structured documents), and finer-grained admin controls layered on top of the audit foundation - tool-usage policies, per-agent egress rules, or approval workflows.
See more alternatives to Tailscale →
See more alternatives to Dust →