Skip to content

Context-heavy PR reviewer · Comparison

Critique CLI
vs Greptile.

Greptile indexes repositories and uses that context for AI PR review. It is seat-priced and aimed at catching cross-file issues once a pull request is open.

updated 2026-08-06CLI finish passcontext-heavy pr reviewer

Quick answer

Greptile deepens PR review with repo context. Critique CLI checks the local change before the PR exists — reconstructs the working tree, returns finish.v1 evidence, and hands control back to your agent. Different moment: pre-commit finish vs post-PR comments.

What is Critique CLI?

Critique CLI is an independent finish pass for coding agents. It reviews the local working-tree change before commit or PR, returns finish.v1 JSON (outcome, evidence, limits, exit codes), and optionally attaches a repair package. It integrates with Codex, Claude Code, OpenCode, and Cursor via `critique integrate`.

Last updated 2026-08-06 · Verify competitor pricing on the vendor site before procurement.

Our pick

Critique CLI

Independent finish check on your working tree. finish.v1 JSON, optional repair packages, integrates with Codex · Claude Code · OpenCode · Cursor.

Install CLI

Full-repo context for pull request comments

Greptile

Greptile is per seat (a 20-person team can land near ~$600/mo). Critique Pro at $49/mo (or Team at $149/mo) is shared across the team for CLI + cloud review usage.

Visit Greptile

Critique CLI vs Greptile: features

CapabilityCritique CLIGreptile
When it runsWorking tree before commitOpen pull requests
Context strategy· Change capsule + disposable workspace checksFull-repo embeddings for PRs
CallerYou or your coding agent via CLIGitHub bot for reviewers
OutputStructured finish.v1 JSONPR comments / UI
PricingShared credits / BYOKPer seat
Repair packageYes (`--repair pack` and verified modes)Comment-first

Verify competitor pricing on greptile.com.

Why teams pick Critique CLI

  • You want the review before the PR, in the same shell as the agent that made the change.
  • Credits beat seats once more than a few people share the tool.
  • You need exit codes and JSON a bot can consume, not only human-readable comments.
  • You want optional repair packages when the finish pass finds a verified defect.

When Greptile is the right pick

  • Your buying center only funds GitHub PR bots and will not adopt a local CLI.
  • You already have Greptile enterprise procurement and only need deeper PR comments.

Common questions

01Is Critique CLI a good alternative to Greptile?

Greptile deepens PR review with repo context. Critique CLI checks the local change before the PR exists — reconstructs the working tree, returns finish.v1 evidence, and hands control back to your agent. Different moment: pre-commit finish vs post-PR comments.

02What does Critique cost compared to Greptile?

Greptile is per seat (a 20-person team can land near ~$600/mo). Critique Pro at $49/mo (or Team at $149/mo) is shared across the team for CLI + cloud review usage. Critique's public pricing is team-shared: Solo $19/mo, Pro $49/mo, Team $149/mo, plus an $8/mo BYOK harness (OpenRouter or CrofAI) and a $5/mo student/OSS lane.

03What does the Critique CLI actually run?

Critique reviews the change in your local working tree (staged, unstaged, deleted, and bounded untracked text). `critique finish` returns finish.v1 JSON: outcome, evidence, limits, and exit codes. Optional repair modes attach a repair package when warranted. Cloud runs are available when you want a clean remote machine.

04Can I use Critique alongside Greptile?

Yes. Many teams keep Greptile for its unique strength (see below) and add Critique as the independent finish pass their coding agents call before claiming a task is done. The CLI does not require uninstalling other tools.

05How do I start with Critique CLI?

Run `npm install --global @critiquedotsh/cli`, then `critique login`, `critique integrate --agent all` (Codex, Claude Code, OpenCode, Cursor), and `critique finish --intent "…" --json` on a real change.

06What is Critique CLI in one sentence?

Critique CLI is an independent finish pass for coding agents. It reviews the local working-tree change before commit or PR, returns finish.v1 JSON (outcome, evidence, limits, exit codes), and optionally attaches a repair package. It integrates with Codex, Claude Code, OpenCode, and Cursor via `critique integrate`.

Compare Critique against other tools

Ranked alternatives list

Next step

Check the change
before it ships.

Install the CLI, authorize once, wire your agents, and run finish on a real working-tree change. Structured evidence — not another comment bot.