Compare

Excellent vs Cursor Bugbot: the agent vendor's reviewer vs an independent one

A verifier that works with any agent, versus the agent vendor's own reviewer.

Cursor Bugbot

Cursor Bugbot in one line

Cursor's automatic pull-request reviewer. Frontier and in-house models read the diff looking for hard logic bugs, fixes hand off to Cursor or a Background Agent, and Bugbot Rules tune what it flags. Cursor has also owned Graphite — stacked PRs, a merge queue and its own AI reviewer — since December 2025.

Best for: Teams whose agent is Cursor and who want review and fix to happen in the window they already have open.
Limits: It is scoped to Cursor's world, and nothing on its page claims it executes your code: the check is a model reading the diff and the surrounding codebase.
Stronger than us at: Signal-to-noise and the fix loop. Cursor publishes that more than 70% of Bugbot's flags get resolved before merge; we publish no equivalent number. A fix is one hop back into the editor the developer is already in. And Graphite is better than us at its own job — stacked PRs and a merge queue — which Excellent does not do at all.
Price 2026-09-23: Not published (Usage-based billing)

Excellent

Excellent in one line

A verification system for agentic tasks — it records what the agent attempted, runs your checks against the claim, and binds the result to evidence you can open.

Best for: Teams that want agent work checked before they trust or promote it.
Limits: There is no hosted option. You run it on your machines. Verification evidence stays on the machine that produced it — it does not sync to teammates yet. No SSO, and no Mac app has shipped. It does not write tests, and it does not review your diff.
Stronger than them at: Keeping the attempt record, running your own checks as the oracle, and trialling prompt, model and tool changes on held-out work from your repository.
Price 2026-09-23: Free to install and run (Consulting from $10,000 / month)

Head to head

The capabilities that decide it

Capability by capability — Cursor Bugbot on the left, Excellent on the right. Prices are the vendor's own, read on 2026-09-23.

Capability	Cursor Bugbot	Excellent
Runs your tests or build Bugbot's page describes reading the diff with codebase context. It makes no execution claim.	No	Yes
Works with agents other than Cursor	No	Yes
Independent of the agent that wrote the code	Same vendor as the agent	Separate from the agent and from its completion claim
Records each agent attempt and the claim it made	No	Yes
Published false-positive discipline We have no published figure. When there is a real one, it will be on this page.	Yes — Cursor states 70%+ of flags are resolved before merge	No
Stacked PRs and merge queue	Graphite, now part of Cursor	No
Published price (checked 2026-09-23) Third parties quote a per-run figure for Bugbot. Cursor does not, so neither do we.	Not published. cursor.com/bugbot lists no price; cursor.com/pricing says only “Bugbot on usage-based billing” on Individual/Pro and lists agentic code reviews with Bugbot as a Teams feature. Graphite: Hobby free, Starter $20, Team $40 per user per month billed annually, Enterprise custom.	Free to install and run. Consulting starts at $10,000 / month.

Also on this page

The rest of the field, named

Close enough to belong in this comparison, not different enough to need a page of their own.

Graphite

Visit

Cursor acquired Graphite in December 2025, so the two now come from the same vendor. Graphite is a review workflow — stacked PRs, a merge queue, Graphite Chat fixing CI failures, and CI that runs only when it needs to. Hobby free; Starter $20 and Team $40 per user per month billed annually; Enterprise custom (checked 2026-09-23). Excellent does none of that, and Graphite gates on your CI rather than writing the checks.

Verdict

When to pick which

If Cursor is your agent and your editor, Bugbot is the path of least resistance, and it is good at what it does. Excellent is the choice when you want the thing checking the work to not be sold by the people who wrote it — and when you want a record of the attempt that outlives the pull request.

Pick Cursor Bugbot if

Teams whose agent is Cursor and who want review and fix to happen in the window they already have open.

Add Excellent if

You want agent work captured as attempts, checked against evidence you can open, and promoted only when the result is defensible to someone outside the team.

Still shopping? See the full list of Cursor Bugbot alternatives →

More matchups

See Excellent against the rest of the category

Excellent vs Tusk

Tusk writes the tests. Excellent proves the attempt — and can take Tusk's tests as the evidence.

Excellent vs CodeRabbit

An LLM reading the diff, versus evidence from checks that actually ran.

Excellent vs Greptile

TREX really does run tests in a sandbox. The difference is the attempt record, not the execution.

Excellent vs GitHub Copilot code review

The reviewer already in your plan, versus evidence from checks that actually ran.

Excellent vs Qodo

Two products describing agent work in similar words — a rules engine on one side, checks that run on the other.

Excellent vs Braintrust

Braintrust evaluates your LLM app. Excellent verifies the code your agent wrote in your repo.

All comparisons

Trust the evidence, not the agent's confidence

Install Excellent, run it beside the agent you already use, and inspect what the checks actually said.

See how it works