AI code reviewer that indexes the whole repository and uses agents to check each pull request for bugs and standards violations. A free Starter tier gives 50 credits a month; Pro is $30 per seat.
Greptile is an AI code review product that builds a graph of a repository, covering files, functions and dependencies, and then uses a group of agents to review each pull request against that context. The company says the review looks at the impact of a change beyond the diff itself and learns team standards by reading comments that engineers leave on earlier pull requests. Teams can also write custom rules in plain English.
Greptile supports GitHub, GitLab, Bitbucket and Cursor Origin. The Enterprise plan adds GitHub Enterprise Server and Enterprise Cloud with data residency, GitLab Self-Managed, Bitbucket Data Center and Gitea, plus Perforce through P4 Code Review for on-premises deployments. Findings can be sent from the review to coding tools such as Claude Code, Cursor, Codex or Devin to fix them. A command line tool, a runtime validation beta and a security review feature are also listed.
Pricing is credit based. The Starter plan is free for one active developer with unlimited repositories and 50 credits per month. Pro is $30 per seat per month with 50 credits per seat, custom review rules, unlimited seats and extra credits at $1 each, with a 14-day free trial. A base review uses 1 credit, a Plus review uses 3 and an Apex review uses 10. Enterprise is custom and adds self-hosting, SSO and SAML, and a dedicated Slack support channel.
Free use is offered to qualified non-commercial projects with an OSI-approved license, and early-stage startups can apply for 50 percent off. Greptile states SOC 2 Type II compliance and says reports are available on request, and its terms allow de-identified data to be used for AI training with an opt-out.
Yes. Starter is free for one active developer, with unlimited repositories and 50 credits per month. Qualified open source projects can also apply for free access.
Pro is $30 per seat per month with 50 credits per seat and a 14-day free trial. Additional credits cost $1 each. Enterprise pricing is custom.
Its terms say de-identified data may be used for AI training, with an account setting to opt out. Self-hosted customers have no data collected for machine learning unless they configure it.
Website: https://www.greptile.com/
Company: Tabnam, Inc.
Whole-repo-context reviewer with a free tier of 50 credits a month; Pro is $30 per seat monthly and extra credits cost $1 each. Credit use rises with Plus and Apex review levels.
| Pricing model | Freemium |
|---|---|
| Free tier | Yes · Starter: 1 active developer, unlimited repositories, 50 credits per month. · 14-day trial |
| Starting price | $30 / month |
| Data residency | Not verified |
| Compliance (as stated by vendor) | SOC 2 (certified) |
| Integrations | GitHub, GitLab, Bitbucket, Cursor Origin, Claude Code, Cursor, Codex, Devin |
| Public API | Not verified |
| Self-hostable | Yes |
| Official site | Online (auto-checked 2026-10-12) |
| Can a general AI assistant replace it? | A general LLM sees only what you paste. Greptile indexes the whole repository and comments on the PR; an LLM alone cannot do either. |
| Last verified | 2026-10-10 by editor |
Open Interpreter is an open-source terminal agent, forked from Codex, that reads and edits files and runs commands inside an OS-level sandbox with approvals. It is free under Apache 2.0 and works with local models through Ollama or LM Studio.
Together AI is a cloud platform for running open models through a per-token serverless API, plus dedicated endpoints, GPU clusters and fine-tuning. Hosted GLM-5.3-Flash, for example, is listed at $0.15 input and $0.50 output per million tokens.
Kimi is Moonshot AI's assistant and model family, offered as the kimi.com agent workspace and as a pay-as-you-go API. The Kimi K2.7 Code model is listed at $0.95 input and $4.00 output per million tokens.
Z.ai offers the GLM model family through a chat app and a developer API billed per million tokens. GLM-5.3-Flash is listed at $0.15 input and $0.50 output, and the API is compatible with the OpenAI SDK.
The Gemini API and Google AI Studio let developers build with Google's Gemini models for text, code, images, video and speech. A free tier covers some models; paid use is billed per million tokens, such as $0.30 in and $2.50 out on Gemini 3.5 Flash-Lite.
The Claude API is Anthropic's developer platform for building apps and agents on Claude models, billed per million tokens. Rates run from Claude Haiku 5.5 at $0.10 input and $0.50 output up to Claude Fable 5.1 at $10 and $50.
Need the outcome rather than the software?