Qodo is an AI code-integrity platform, formerly known as CodiumAI before rebranding on September 30, 2024, that focuses on agentic pull-request review, regression-testing, and in-IDE code generation rather than pure autocomplete. Its best-known product, Qodo Merge, grew out of the popular open-source PR-Agent project, and the company positions its whole suite around helping teams maintain code quality as more code gets written by AI.
Who builds it
- Built by Qodo (formerly CodiumAI), founded in 2022 and rebranded to Qodo in September 2024 to signal a move beyond test generation toward broader "code quality."
- Qodo Merge is the direct successor to PR-Agent, the company's earlier open-source pull-request review tool.
Core features
- Qodo Merge: agentic AI pull-request review across GitHub, GitLab, and Bitbucket, with cross-repository context to flag breaking changes and dependency conflicts.
- Qodo Cover: an autonomous regression-testing agent that generates and validates tests.
- Qodo Gen: context-aware code and test generation inside the IDE.
- Living Rules System: a self-learning rules engine that enforces organization-specific coding standards and evolves over time.
- Command: a CLI tool for terminal-based, agentic quality workflows.
- Supported IDEs include VS Code, the JetBrains suite (IntelliJ, PyCharm, WebStorm, GoLand, CLion, RubyMine, PhpStorm), and Visual Studio; supported Git platforms include GitHub, GitLab, Bitbucket, Azure DevOps, and Gerrit (Enterprise).
- Qodo reports the highest F1-score on an AI code review benchmark and claims roughly 1 hour saved per PR, with about 90% of initial review handled before a human steps in — vendor-reported figures rather than independently audited ones.
Pricing
- A free 14-day trial with unlimited reviews and credits, no credit card required.
- Pro Team: $30/month, designed for organizations up to 30 users, with credit packs at three tiers (2,500 credits ≈ 18 reviews/month, 5,000 credits ≈ 36 reviews/month, 20,000 credits ≈ 144 reviews/month) that can be switched or topped up anytime.
- Enterprise: custom pricing for 30+ users, adding SSO/SAML, audit logs, a governance analytics dashboard, bring-your-own-LLM-keys (BYOK), and single-tenant SaaS or on-premises deployment.
- A separate, dedicated free program exists for qualifying open-source projects.
Who it's for
Qodo suits engineering teams that want an AI layer specifically focused on review and test quality — catching bugs, enforcing standards, and generating meaningful tests — rather than a general-purpose autocomplete or autonomous coding agent. Its multi-IDE and multi-Git-platform reach makes it a fit for teams standardized on any of the major stacks, while the Enterprise tier's on-prem and BYOK options target larger organizations with stricter data-governance requirements.