AI coding environment with agents, a CLI and cloud agents, plus Bugbot for pull request review on Teams plans. The Hobby plan is free; Pro is $20 a month and Teams is $40 per user.
Cursor, made by Anysphere, is an AI coding environment described by the company as a coding agent for building software. The desktop app is an editor with agents that plan and edit code, and Cursor also offers a command line interface, cloud agents that run tasks on their own machines, automations, a mobile app and a plugin marketplace. A Composer model is available alongside other frontier models.
For pull requests the company sells Bugbot, an AI code reviewer that integrates with GitHub and looks for logic bugs with a low false positive rate. The Bugbot page says all plans have a 14-day free trial. The pricing page lists Bugbot as usage-based on Pro plans and agentic code reviews with Bugbot as included in the Teams plan. The main page shows a macOS download, and cloud agents are reachable on the web.
The pricing page lists four plans. Hobby is free with no credit card and limited agent requests. Individual plans start at $20 per month for Pro, with Pro+ and Ultra for heavier use, and add extended agent limits, cloud agents and access to frontier models. Teams is $40 per user per month and adds shared billing, a team marketplace, usage analytics, team-wide privacy mode and SAML or OIDC single sign-on. Enterprise is custom and adds pooled usage, SCIM, audit logs and access controls.
Cursor says privacy mode guarantees that code data is not used for training by Cursor or its model providers when enabled. The site footer shows SOC 2, ISO 27001, ISO 42001 and AIUC-1 badges.
Yes. The Hobby plan is free with no credit card and limited agent requests. Pro is $20 per month and Teams is $40 per user per month.
Bugbot is Cursor's AI pull request reviewer, built to find logic bugs in GitHub pull requests. It has a 14-day free trial and is included in the Teams plan; Pro uses usage-based billing.
With privacy mode on, Cursor guarantees code data is not used for training by Cursor or its model providers. Team admins can enable it team-wide.
Website: https://cursor.com/
Company: Anysphere, Inc.
AI coding editor first, with Bugbot as an add-on PR reviewer. Hobby is free; Pro is $20 a month. Bugbot is included on Teams at $40 per user and billed by usage on Pro. Review is not its main product.
| Pricing model | Freemium |
|---|---|
| Free tier | Yes · Hobby: no credit card, limited Agent requests, access to Composer. |
| Starting price | $20 / month |
| Data residency | Not verified |
| Compliance (as stated by vendor) | SOC 2 (claimed), ISO 27001 (claimed) |
| Integrations | Not verified |
| 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 can suggest code but cannot edit your project or comment in a GitHub PR. Cursor and Bugbot are needed for that; the editor still uses LLMs inside. |
| 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?