Harness bought Augment’s coding agents to show them what happens after the merge

Harness announced Thursday that it acquired Augment Code’s Cosmos software factory, Auggie CLI and Code Context Engine, along with the team behind them, for an undisclosed amount. The deal adds autonomous coding agents to Harness’s existing software delivery platform, which already handles testing and deployment.

According to Harness, Cosmos will become the Harness Cosmos Software Factory Agent, and the company says the connection between Augment’s codebase understanding and Harness’s delivery history is already live. Cosmos, the Code Context Engine and the Software Delivery Knowledge Graph are linked to Harness through the Model Context Protocol (MCP), so teams writing code in Cosmos today have context from across the software development lifecycle available to the agent as it works.

“AI’s impact on software will not be measured by how much code it generates, but by how much valuable software reaches customers.”

“AI’s impact on software will not be measured by how much code it generates, but by how much valuable software reaches customers,” said Harness founder and CEO Jyoti Bansal. The acquisition follows the company’s research into the AI velocity paradox, which found that faster code generation was putting additional strain on testing and release processes that had not kept pace.

Inside the Cosmos factory

Cosmos takes a requirement or bug report through to a pull request, with agents writing and testing code inside isolated VMs. They can also pick up failed checks and review comments on an existing PR, using feedback from earlier rounds to make further changes.

Teams can fork and customize agents for their own workflows, while Augment’s Code Context Engine retrieves relevant codebase context as they work.

“We set out to bring AI to the entire software development lifecycle, starting with context-aware coding,” said Igor Ostrovsky, Augment Code’s co-founder and CTO, describing engineering work that becomes increasingly autonomous “with engineers stepping in only where judgment really matters.”

“We set out to bring AI to the entire software development lifecycle, starting with context-aware coding, with engineers stepping in only where judgment really matters.”

Where humans still approve

Developers still approve and merge changes, although Bansal wrote that teams can decide which work agents handle on their own and where a person has to review or approve it. Cosmos is still reached through Augment’s existing site, but it’s already connected to Harness’s delivery platform over MCP, which means the agent has Harness’s deployment history and security findings in hand no matter where developers open it.

Turning failures into fixes

Harness has connected Augment’s Code Context Engine to its Software Delivery Knowledge Graph over MCP, which gives Cosmos access to deployment history and security findings when it works on code changes. A Harness spokesperson tells The New Stack, the division of labor in terms of what each system knows, with code context telling the agent what the code does and the delivery graph telling it what happens once that code ships, so the agent can write changes that are safe to deploy rather than ones that are only correct in isolation.

“When Harness downstream agents identify an issue while testing, securing, or deploying code, they send it back to Cosmos with the context to fix it,” Bansal said. A failed deployment goes back to Cosmos for another revision, carrying the failure context to the coding agent instead of leaving a developer to diagnose the issue and open a separate task.

Harness hasn’t detailed how agents decide which deployment records or security findings to pull from the graph for a given change, a question that matters for teams weighing how much production history an agent should see before it touches their code.

Who controls agent permissions

Harness plans to bring Cosmos under the identity and policy controls of its Agent Harness but has not explained how permissions work across the two systems, a gap that stands out as the industry moves toward agent identity, with Microsoft giving its Copilot agents identities of their own.

Cosmos runs agents in isolated VMs with configurable review checkpoints, although it’s unclear what production data they can access through the delivery graph or which downstream actions they can take once a failure is handed back to them. Those limits deserve scrutiny, particularly after coding agents exposed more than 13,000 screenshots through routine workflows without an attacker ever gaining access.

Update, Oct. 12, 2026: This story has been updated to reflect that Harness says the integration between Cosmos and its Software Delivery Knowledge Graph is already live via MCP; an earlier version said the integration had not shipped.