Event-driven always-on autonomous coding. Triggers from GitHub PRs, Slack, Linear, PagerDuty, cron, webhooks. Cloud sandboxes with user-configured instructions, MCPs, and models. $2B ARR, $29.3B valuation. Launched Mar 5, 2026.
Where it wins
Only contender with event-driven triggers (Slack, PagerDuty, Linear, webhooks, cron)
Each automation spins up a cloud sandbox with user-configured instructions, MCPs, and models
$2B ARR (doubled in 3 months), $29.3B valuation
Named customers: OpenAI, Midjourney, Perplexity, Shopify
35% of Cursor's own PRs merged by agents
60% corporate revenue share
Where to be skeptical
Launched Mar 5, 2026 — 12 days old, zero independent validation
HN engagement on Automations: 7 pts — near-zero community signal
Locked to Cursor IDE — teams on VS Code/JetBrains face full migration
35% self-merge claim is self-reported
Editorial verdict
Most innovative architecture in the category — event-driven triggers are genuinely new. But 12 days old with zero independent validation. Needs 30+ days of production evidence before confidence can increase.
Videos
Reviews, tutorials, and comparisons from the community.
Introducing Automations: always-on coding agents
Cursor Automations Clearly Explained (worth learning?)
Related
Claude Code
98Anthropic's official agentic coding CLI. v2.1.81 (Mar 20) shipped `--bare`, smarter worktree resume, and improved MCP OAuth while the repo crossed 82,204 stars and logged ~14 commits/week across 10+ maintainers. Terminal-native, tool-use-driven, with deep file system + shell access, #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue. 8M+ npm weekly downloads. Opus 4.6 with 1M context.
OpenHands
88Category leader in multi-agent orchestration — 69,352 stars (verified), $18.8M Series A, AMD hardware partnership, 455 contributors, 1M downloads/month PyPI (3.4M all-time). SWE-Bench Verified 72% with Claude 4.5 Extended Thinking (updated 2026-03-19), Multi-SWE-Bench #1 across 8 languages. Gap to #2 is enormous on every axis.
Gemini CLI
88Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (60 req/min, 1K req/day). v0.35.0 (Mar 24) shipped keybinding, policy, and telemetry fixes while the repo hit 98,957 stars and 12,593 forks. Terminal-Bench 2.0: 78.4% (#1). SWE-bench Pro standardized 43.30% (#3). Plan Mode added March 2026. First-pass correctness ~50-60% (Educative.io).
Codex CLI
87OpenAI's open-source coding agent built in Rust. Terminal-Bench 77.3% (#2), SWE-bench Pro standardized 41.04% (GPT-5.2-Codex). GPT-5.4 shipped March 5, 2026. Codex Security agent adds appsec capabilities. 3-4x more token-efficient than Claude Code, 240+ tokens/sec. Free with ChatGPT subscription, sandbox-first execution. 1M+ first-month users. Cleanest security record in Tier 1 — no documented incidents.
Public evidence
Event-driven triggers (GitHub PRs, Slack, Linear, PagerDuty, cron, webhooks). Each automation runs in cloud sandbox. Closest thing to a literal software factory.
$2B ARR doubled in 3 months. 60% corporate revenue share. Customers: OpenAI, Midjourney, Perplexity, Shopify.
35% of Cursor's own PRs merged by their automation agents. Hundreds of automations per hour.
Cursor scores 50.2% on SWE-bench Pro with custom scaffolding — marginally ahead of Claude Code's 49.8%. Strongest Pro score among IDE-integrated tools.
Enterprise customers now 60% of Cursor revenue. Validates that Cursor is not just an indie developer tool. Named customers: OpenAI, Midjourney, Perplexity, Shopify.
Raw GitHub source
GitHub README could not be fetched right now.