Malleon – turn real user sessions into automated tests
Session replay to test converter, but Replay.io and LogRocket already pivot toward this.
AI-powered browser testing that writes and replays its own test scripts. Describe tests in plain YAML; QAA uses Gemini to drive the browser on the first run, records every action, then replays them directly — no AI needed on repeat runs.
Record-once replay pattern beats hand-coded Selenium, but UI clarity and multi-browser support unclear.
QA engineers, test automation practitioners
Playwright · Cypress · Selenium
Session replay to test converter, but Replay.io and LogRocket already pivot toward this.
Agent testing platform, but screenshot only shows login page—no actual product demo or proof.
Standardizes portable cryptographic receipts for agent behavior—but adoption unclear, overlaps Nobulex heavily.
120+ built-in test playbooks with JSON output agents can read and fix.
SkillForge turns the old 'show, don't tell' trick into code: record a task, and their AI teases clicks, keystrokes and navigation out of pixels into a stepwise skill file you can edit and export. The ability to trim video, rewrite steps via AI, and output a SKILL.md for agent frameworks is a practical, opinionated workflow that could shortcut lots of brittle RPA scripting — my main questions are reliability across dynamic UIs and privacy/recording controls, but the product direction is smart and tangible.
The write-up zeroes in on a concrete, painful failure mode: MCP setups streaming full DOMs and logs into models and burning token budgets. It shows how playwright-cli keeps browser state external and emits compact element references and YAML flows you can replay into npx playwright test — a realistic pattern for long agent sessions. Valuable practical guidance for teams already on Playwright, but it's an explainer, not a new system you can drop in without plumbing.