Code TerrierCode Terrier vs Greptile
Greptile is an AI code review tool that prices per active developer ($30/dev/month) with 50 reviews included, then $1 per review after that. Code Terrier uses a free shared model pool or bring-your-own-key, with no per-seat cost and no per-review metering — an auto-mode commit triggers a fresh review at no per-review charge.
The structural differences that matter: Code Terrier's architecture supports up to three model families; the current shared pool uses one configured model, passes findings through verification, and quietly closes findings that no longer apply when you push a fix in auto mode. Greptile has no permanent free tier for private repos and uses a codebase-graph context built on agent v4.
| Criteria | Code Terrier | Greptile |
|---|---|---|
| Pricing | Free 50-credit pool, Pro $5/$50, or BYOK | $30 / dev / month incl. 50 reviews, then $1/review |
| Free tier | Yes, private repos included | 14-day trial, no permanent free tier |
| Review models | Architecture up to 3; shared pool uses 1 today | Single model with codebase-graph context |
| Findings format | Inline, categorized (Security/Bug/Flag/Slop) | Inline comments with codebase context |
| Verification | Independent verifier (maker/checker) | None |
| Approves or auto-merges | Never | No |
| Key control | Your own key, or no key at all | Vendor key only |
The review architecture supports up to three model families. The current shared pool uses one configured model; near-duplicate findings are merged when multiple reviewers are configured, then the verification stage checks line legality before publication.
A single model with codebase-graph context (agent v4). No independent maker/checker verification stage.
Free tier on a shared model pool, or BYOK so reviews run on your own Anthropic or OpenAI-compatible account. No per-seat cost and no per-review metering.
Per-active-developer pricing ($30/dev/month) that includes 50 reviews, then $1 per review. Cost scales with headcount and review volume.
Quiet, evidence-backed findings on the exact changed line. No comment at all on clean changes; findings are capped and trimmed by severity.
Inline comments enriched with codebase-graph context. Useful when deep context helps, but the single-model review is not independently verified.
In auto mode, a new commit starts the next review. Prior human comments are carried as bounded, untrusted context, and findings that no longer apply close quietly.
Re-reviews on new commits with codebase context; behavior on rejected findings across pushes is not a documented, durable disposition model.
Code Terrier's architecture supports up to three model families; the current shared pool uses one configured model and verifies findings before publication, while Greptile uses a single model with codebase-graph context. Code Terrier has a permanent free tier for private repos and supports BYOK; Greptile prices per active developer ($30/dev/month) with 50 reviews included and no permanent free tier.
Yes. The shared model pool is free and works on private repos. Greptile's free tier is a 14-day trial only.
No. Code Terrier only posts COMMENT reviews. It never approves, never auto-merges, and never pushes or commits code.
Install Code Terrier and open a pull request. It only posts COMMENT reviews; it never approves or auto-merges.