Code review platform synced with GitHub that combines stacked pull requests, a merge queue, a PR inbox and AI reviews. The Hobby plan is free for personal repos; paid plans start at $20 per user billed annually.
Graphite is a code review platform built around GitHub. Its signature feature is stacked pull requests, which break a large change into small, sequenced pull requests so that work continues while earlier ones are under review. A command line tool and a VS Code extension create and manage the stacks and wrap everyday git commands, and a stack-aware merge queue lands the pull requests in order.
Graphite also provides a new pull request page, a unified inbox for the team's reviews, Slack notifications, insights on team review activity, CI optimization and AI features. Graphite Chat is an assistant on the PR page that can explain changes, fix CI failures and apply suggested fixes, and AI Reviews comment on each pull request with suggested fixes. The site notes that Cursor cloud agents are now available inside Graphite.
The pricing page lists Hobby as free for personal account repositories, with limited AI reviews and limited chat. Starter is $20 per user per month, billed annually, and covers all GitHub organization repositories with Slack notifications and team insights. Team is $40 per user per month, billed annually, with unlimited chat, unlimited AI reviews, review customizations, automations and a merge queue. Enterprise is custom and adds SAML, audit logs, GitHub Enterprise Server support and service level agreements.
Graphite offers a free first 30 days without a credit card. A toggle shows annual billing at 20 percent off, so month-to-month rates are higher but were not shown. No compliance certifications were listed on the pages read.
The Hobby plan is free for personal account repositories, with limited AI reviews and chat. Graphite also offers a free first 30 days without a credit card.
Starter is $20 per user per month and Team is $40, both billed annually; annual billing is shown at 20 percent off. Enterprise pricing is custom.
The site describes GitHub sync and GitHub organization support. GitHub Enterprise Server support is an Enterprise feature, and other Git hosts are not mentioned.
Website: https://graphite.com/
Stacked-PR workflow tool with AI review, merge queue and inbox, GitHub only. Hobby is free; Starter is $20 per user billed annually. Unlimited AI reviews start on the $40 Team tier.
| Pricing model | Freemium |
|---|---|
| Free tier | Yes · Hobby: personal account repos, limited AI reviews and Graphite Chat. · no credit card required · 30-day trial |
| Starting price | Not verified |
| Data residency | Not verified |
| Compliance (as stated by vendor) | Not verified |
| Integrations | GitHub, Slack, VS Code |
| Public API | Not verified |
| Self-hostable | Not verified |
| Official site | Online (auto-checked 2026-10-12) |
| Can a general AI assistant replace it? | A general LLM cannot stack branches, run a merge queue or comment in the PR. Graphite handles the workflow; an LLM can only review pasted code. |
| 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?