Recurse
Recurse is an AI-powered code review tool that integrates with Claude Code and Cursor to automatically catch bugs and suggest fixes. It understands your full codebase and library dependencies, helping developers reduce review time by up to 80%.
Key facts
What is Recurse?
Cut code review time by 80% by automatically identifying bugs and breaking changes before they're introduced.
Who is Recurse best for?
Developers and engineering teams using AI coding assistants
What are its main limitations?
- Limited pricing details available (only one plan publicly listed)
- SOC 2 compliance still in progress
- No explicit free tier beyond the 14-day trial
Limitations are based on product materials or editorial synthesis; confirm on the official site.
Key features
- ✓Full codebase understanding
- ✓Expert knowledge of every library
- ✓Detect breaking changes and suggest fixes
- ✓Code analysis and PR intelligence
- ✓Customisation
- ✓Zero retention policy on code
- ✓SOC 2 compliance in progress
Use cases
- →Catching critical bugs before they reach production
- →Reducing debugging time by 80%
- →Ensuring new contributions remain consistent with existing code
- →Speeding up the code review process without sacrificing quality
- →Teaching developers to write cleaner, safer code
Pricing
Free Trial
$0
- · 14-day free trial
Pro
$25 one-time
- · Full codebase understanding
- · Expert knowledge of every library
- · Code written the way you want
- · Unlimited access to CLI tool rml
- · Integration with Claude Code and Cursor
- · GitHub PR review bot
Free 14-day trial available; Pro plan at $25 one-time payment.
Pros
- +Caught critical bugs that would have made it to production
- +Improves developer skills by highlighting issues and quick-win improvements
- +Zero retention policy ensures code privacy
- +Seamless integration with popular coding assistants
Cons
- −Limited pricing details available (only one plan publicly listed)
- −SOC 2 compliance still in progress
- −No explicit free tier beyond the 14-day trial
Positioning
- Core value: Cut code review time by 80% by automatically identifying bugs and breaking changes before they're introduced.
- Ideal for: Developers and engineering teams using AI coding assistants
- Product type: Integration with Claude Code and Cursor; CLI tool (rml); GitHub PR review bot
Frequently asked questions
Why choose Recurse?
Recurse automatically identifies bugs and breaking changes before they are introduced, saving up to 80% of debugging time.
How does Recurse work?
It integrates with coding assistants (Claude Code, Cursor) and analyzes code against your full codebase and library knowledge, then suggests fixes for any issues found.
Does Recurse store my code?
No. Recurse has a zero retention policy and does not train models on your code. The analysis is performed in real time and then wiped.
What are Recurse usage limits?
The Pro plan includes unlimited access to the CLI tool rml. Specific limits are not detailed on the homepage.
You may also like
Curated suggestions based on similar categories.
Rescript
ReScript is a strongly typed programming language that compiles to clean, efficient JavaScript. It is designed to be readable by both humans and AI tools, providing a fast compiler and static type system for building JavaScript, Node, and React applications.
LongCat-2.0
LongCat-2.0 is a next-generation, open-source MoE (Mixture of Experts) model with 1.6T total parameters, designed for agentic coding and featuring native 1M token context support. It achieves state-of-the-art performance on software engineering and terminal benchmarks, and is available on longcat.ai and OpenRouter.
VibeCoding
Dharmesh Shah's proposed idea for a community platform called VibeCoding.com, designed to connect vibe coders with professional developers. The free tier allows browsing and learning from others, while the paid tier lets users post issues (e.g., GitHub repos) and receive paid professional help, creating a marketplace.
Cursor
Cursor is an AI-powered coding agent that helps developers build software faster by integrating directly into their workflow. It offers context-aware code completions, autonomous agents, cloud-based execution, and integrations with tools like Slack and GitHub, all while supporting multiple frontier models.
CodeRide
CodeRide is a project management tool for AI coding agents that uses MCP (Model Context Protocol) to break project documentation or PRDs into optimized, fully contextual tasks. It maintains persistent context between coding sessions, eliminating the need to re-explain project architecture, coding patterns, and goals.
Gauge
Gauge is a free and open source test automation framework focused on acceptance testing. It uses Markdown-based specifications for readable and maintainable tests, supports multiple languages, and offers features like parallelization, plugins, and failure screenshots.