Tabnine
TabnineCode completion that can run on-premises, with a per-team model trained on your repos.
Test generation and code review wired into the pull request.
Raising test coverage on existing code without writing every case by hand
Architectural review — it tests what exists, not what should
A code assistant focused on the review and test side: it generates tests for a diff, flags risky changes, and comments on a pull request. The useful constraint is that its output is reviewable in the place reviews already happen, which makes the trust decision cheap.
Code completion that can run on-premises, with a per-team model trained on your repos.
Completion and chat built into the editor most teams already use.
Open-source IDE assistant you can point at any model.
3 alternatives overlap with this one. Compare them →
A deliberately exhaustive reference server that exercises prompts, resources, tools, sampling, and notifications. You do not install it to get work done; you install…
Drives a real browser through accessibility snapshots rather than screenshots, so an agent can click, type, and assert without a vision model. This is the practical …
Serves version-specific documentation for thousands of libraries, so an agent stops writing code against an API that changed two releases ago. The practical fix for …
Engineering skills aimed at production code: review, testing, refactoring, and release hygiene.
Official skill for driving a browser to test a web app and reporting what broke.
A design-quality skill that hunts the tells of AI-generated interfaces.