Harness creates source code management for agent-ready development

Harness introduced Agent-Ready Harness Code Repository and AI Code Review, a source code management and review system designed for AI coding agents, featuring agent-specific permissions, MCP and CLI support, and AI Checks that gate merges. CEO Jyoti Bansal said the entire SDLC must become autonomous, with repository, review, pipeline, and governance working as one system.

Harness creates source code management for agent-ready development Harness today announced it has addressed the adoption and challenges of AI coding agents by introducing a new code repository and a code review tool that work as one experience for developers. Agent-Ready Harness Code Repository was created to replace legacy SCM systems that weren’t built to handle the volume of code and pull requests generated by AI coding, which has resulted in pull requests piling up, search and indexing lag, and “a permission system designed around developers that has no good answer for an agent that might merge code on its own,” the company wrote in its announcement. The new repository uses agents to keep up with code changes, gives agents their own permissions, and was built to be used by humans and agents through MCP and CLI. AI Code Review looks at the code and offers review information that humans can use to make informed decisions as to what ships and what doesn’t. AI Checks can be set up by account or by project and acts as a gate for allowing merges. If, for instance, a change fails a required check, it cannot be merged. Further, when diffs occur, they are grouped by risk and are surfaced to the top so as not to be lost under mass renames and dependency bumps, the company wrote. Finally, it provides feedback as to what a change might put at risk before a pull request is even opened. If the feedback is found to be valid, the merge can be done with one click. “Software delivery is going through its biggest shift since the move to the cloud, and the systems we all built our workflows around were designed for a different scale and a different kind of user,” said Jyoti Bansal, CEO and co-founder of Harness, in the announcement. “You do not solve that by adding AI features to a repository designed fifteen years ago. The entire SDLC has to become autonomous, which means the repository, the review, the pipeline, and the governance must all work as one system.” SD Times Q&A What is Harness Agent-Ready Code Repository and how does it differ from legacy SCM? Harness Agent-Ready Code Repository is a source code management system built to handle the high volume of pull requests and code changes generated by AI coding agents. Unlike legacy SCM systems, it gives agents their own permission sets, uses agents to track code changes in real time, and supports both human and agent workflows via MCP and CLI interfaces. How does Harness AI Code Review work with pull requests? Harness AI Code Review analyzes code changes and surfaces review information to help developers decide what ships and what doesn’t. Diffs are grouped by risk level and surfaced to the top of the review queue, and the tool can flag what a change might put at risk before a pull request is even opened. If the feedback is accepted, the merge can be completed in one click. What are Harness AI Checks and how do they gate merges? AI Checks are configurable quality gates that can be set at the account or project level within Harness. If a code change fails a required check, it is blocked from being merged. This allows teams to enforce policy-based governance over AI-generated code before it reaches production. Does Harness Code Repository support MCP for AI agent integration? Yes, the Harness Agent-Ready Code Repository is built to be used by both humans and AI agents through MCP Model Context Protocol and CLI. This allows AI coding agents to interact with the repository programmatically alongside human developers.