Qodo builds context into AI code review with Codex

Qodo builds AI tools for code review and software quality that give coding agents the organizational knowledge needed to understand the code they change. Co-founder and CEO Itamar Friedman calls Qodo "the coding agent's best friend." Qodo uses OpenAI models, including GPT-6 Astra, to gather engineering knowledge, review code, and monitor software quality, and its Codex plugin brings that context and review into developers' coding sessions.

In customer environments spanning 10,000 or more repositories, a local code change can break a downstream service even if it looks correct on its own. Qodo's plugin, built in the Codex marketplace, gives Codex access to codebase knowledge, organizational rules, and independent review through Qodo's Agentic Toolbox, letting it account for dependencies across repositories, including those hosted by different Git providers or connected through Kafka. Before Codex writes code, it can retrieve relevant codebase rules and pull request history; after changes are made, Qodo reviews them and returns findings to Codex in the same session before a pull request is opened.

Itamar describes coding and review agents as "yin and yang," with a vision of agents discussing findings and surfacing only what they don't accept for human review, making developers planners and reviewers. Internally, AI Developer Relations Lead Nnenna Ndukwe uses GPT-6 Astra's Extra High and Ultra effort settings for automated workflows and knowledge work. Itamar also sees opportunity in OpenAI's Decisions API to select which rules and agent skills apply at each development stage, making selection faster and cheaper while improving review quality. Qodo's approach aims at a customer-owned "software factory" combining AI and traditional software engineering, with OpenAI.

(Source：OpenAI)