Codeium
AgentDesktop command center for running multiple AI coding agents locally or in the cloud
- Freemium
- Hosted agent
- Generative code
Desktop command center for running multiple AI coding agents locally or in the cloud

Reviews a branch or PR in two parallel passes: repo coding standards and match to the spec

Implements work from a spec or ticket using test-first slices, then reviews and commits

Ruleset that makes AI coding agents write less code that still works

Runs source-first security reviews with sandboxed checks and evidence-graded findings

Applies Python, JavaScript/TypeScript and Go security guidance to new code or reviews

Lists review threads on the current branch's GitHub PR and fixes the ones you pick

Use ChatGPT on the web to plan and review while Codex executes your coding tasks

Finds C# API changes that break or drift from TypeScript and JavaScript clients

Audits an iOS app's code and metadata for likely App Store rejection risks

Generates a project architecture blueprint document by analyzing a codebase's structure

Generates a prompt that makes the agent find representative code exemplars in a codebase

Lets an agent create persona-targeted CodeTour walkthroughs that link to real code lines

Guides an agent to explore code through a Codebase Memory graph with verification steps

Writes commit messages that explain why a change was made, in Conventional Commits format

Runs repeated Copilot code review rounds on a pull request, fixing and replying to threads

Guides the agent through C# async best practices for naming, returns, exceptions

Audits whether docs still match the code, config and commands, without editing anything

Reviews and shapes .NET/C# code against conventions for documentation, DI, async, testing

Reviews C#/.NET code for design pattern use and suggests improvements without editing it

Generates Copilot instructions from the differences between two versions of a codebase

Generates a full GitHub Copilot configuration for a new project from its tech stack

Guides an agent through writing and reviewing Spring Boot 3/4 application code

Guides agents to write only the source comments that carry non-obvious information

Coaches junior developers through Socratic questions instead of handing them answers

Guides agents to design code where common mistakes cannot be written at all

Runs repeated grading passes over a subject until its findings stop changing

Reviews PostgreSQL code for JSONB, array, schema, function and RLS best practices

Walks through PR review comments one by one and plans fixes or replies before editing

Opens a browser dashboard of your GitHub pull requests filtered by date and role
The most popular AI tools, agents, MCP servers and skills for code review on AI-Powered right now are Codeium, Code review, Implement, ponytail and Security audit. Rankings combine upvotes, recent activity and, for open-source projects, GitHub stars.
Yes. Of the 152 AI tools, agents, MCP servers and skills for code review listed, 109 are free or open source and 23 have a free plan. Use the Pricing filter to see only those.
AI-Powered lists 152 AI tools, agents, MCP servers and skills for code review. New listings are added daily from the official MCP Registry, GitHub and maker submissions.