We made a short video of how Aperture Bot works. You comment /aperture and a task on an issue. It plans the change, makes it, and runs Agent Check (parses, imports, types and your own tests). If anything is red, nothing is pushed. It can also review pull requests, answer questions on the thread, and learn from your reviews, and your own agents can call the same checks over MCP. It's open source and runs as a GitHub Action.
Try it signed out: https://aperturesais.grok.me/bot. I'd love to hear what checks you'd want it to run.
Since launching on 4 Oct, I've merged 55 changes. Here's what you can use now.
Safer Apply
- Every check run gets a verification id, a hash of the staged code, the base, the package.json scripts, the lockfile and the hook scripts. If anything changes before you press Apply, Apply waits and the checks run again.
Since launch, your bots and agents can check a change before they apply it.
Aperture is now an MCP server. Grok Bot, Claude Code, Cursor or any MCP client can call check_change before it applies a change. It checks that the files parse, the imports resolve, and the TypeScript compiler finds no new errors, including in files the agent never opened. It also flags a change that skips or cuts short the tests. Nothing the agent sends is run or kept. Setup takes three steps at https://aperturesais.grok.me/agents
Aperture Agent Check runs the same checks on every pull request, as a CLI or a GitHub Action. Red lines get annotations right on the diff. If a failure was already there in the base branch, it shows as amber, not blamed on the PR. Your code never leaves the runner. Aperture's own PRs go through it.
Honest numbers: in the benchmark, the editor catches 27 of 33 bad edits, with 1 false alarm in 15 good ones. check_change stops 20 of the 33 without running anything. The other 7 only show up when tests run, so keep running them. Every miss is listed at https://aperturesais.grok.me/ben...