Ably vs Cursor
Side-by-side trajectory, velocity, and editorial themes.
Ably pivots its developer surface toward AI agents as first-class consumers
Ably's developer surface has been visibly pivoting toward AI agents over the last six weeks. The CLI hit v1.0 with structured JSON output envelopes, hint fields for self-healing agents, and unified --force semantics. Two weeks later v1.1 added `ably init`, which installs the CLI plus Agent Skills bundles directly into Claude, Cursor, Windsurf, and VS Code in one step. A new AI Transport SDK lands separately, with end-to-end tool-calling and React providers for the Vercel AI SDK.
Ably is building two integration stories in parallel — agents as CLI users (via Agent Skills) and agents as transport consumers (via the AI Transport SDK). Together they bracket the workflow: agents read live data through the SDK and operate Ably itself through the CLI. The traditional client-library stream (JS, Python, Laravel) continues at steady pace in the background, with LiveObjects formally graduating to GA on the protocol-6 update.
Expect the AI Transport SDK to add tool-call adapters for at least one more AI runtime beyond Vercel — most likely the OpenAI Agents SDK or Anthropic's Claude Agent SDK — and Agent Skills coverage to expand to additional AI clients (Cline, Aider, Continue). Watch for the LiveObjects API to surface inside the chat/AI surfaces.
Stacking platform plays — SDK, security agents, fleet environments — in a single sprint.
Cursor is firing on multiple platform-expansion fronts at once. In the past month it has shipped: a programmable SDK that exposes its agent runtime to third-party developers, a Security Review surface with always-on PR security and vulnerability-scanning agents, configurable multi-repo development environments for cloud agents, and admin-side controls (model gating, soft spend limits, granular usage analytics). The cadence is weekly; the substance is platform-grade rather than feature-grade.
Cursor is migrating from "AI-native IDE" to "platform for AI engineering at organizational scale." The SDK turns it into infrastructure for other builders, Security Review creates a recurring always-on agent surface inside customer codebases, and multi-repo environments make fleets of parallel agents actually plausible in real engineering setups. Each release lowers the marginal cost of running many agents against one company's code.
Expect a bundled "agent fleet" tier for enterprise — environments, security agents, SDK access, model governance, and seat-level analytics priced together — within a quarter. Watch for tighter hooks into CI and observability so the output of these agent fleets becomes auditable and measurable, not just shippable.
See more alternatives to Ably →
See more alternatives to Cursor →