currents-dev/currents
Currents gives AI agents the test results your CI records, from Playwright, Vitest, Jest and more. Self-healing tests: an agent gets the errors, traces and history behind a failure, finds the root cause and fixes the test, flaky ones included. Proof of work for any change, not just tests: before-and-after screenshots, videos and Playwright traces from CI, or a demo the agent records in a browser, posted as evidence in the pull request. Teams also use it to reproduce bugs, verify fixes, rank flaky and slow tests, quarantine tests and integrate with GitHub, Gitlab, Slack, Jira, Linear and more.
Experimental. Prove a change works in a browser you drove yourself, when there is no test to run — reproduce a bug, fix it, and post before/after evidence on a pull request or issue. Use when asked to "reproduce this", "show the bug", "prove the fix", "record a session", "capture before and after", or to demonstrate a change on a ticket that has no automated test. Records the browser as a Currents run and returns links that read without a Currents login. For evidence from tests that already run in CI, use collect-evidence instead.
Show that work you implemented actually works, or demo it, from tests that ran in CI via Currents — a trace link whose digest, filmstrip and accessibility snapshots read inside a comment, plus screenshots, attachments and videos. Use when asked to "collect evidence", "prove it works", "show me it works", "demo the feature", "capture a before/after", or to attach proof of a change to a PR, issue, ticket, or status update. Evidence comes from CI runs retrieved through the Currents MCP tools or REST API, not from a local run.
Fix tests that failed in CI, using the results Currents recorded — errors, steps, traces, screenshots and console output. Use when CI is red, a pull request check failed, a build broke, someone asks why a test failed, or you are given a Currents run or test link. Works from a developer's machine or from a CI job that runs after the tests failed.