Devin ships native GitHub Stacked PR support

// 1h agoPRODUCT UPDATE

Devin ships native GitHub Stacked PR support

Cognition has announced native support for GitHub Stacked PRs within Devin, its AI software engineer. This new capability allows Devin to decompose large code modifications into smaller reviewable diffs, fix pull request comments across entire stacks, and automatically rebase downstream changes.

// ANALYSIS

Hot take: Native stacked PR support elevates AI coding agents from isolated task solvers to true production-grade engineering teammates capable of managing complex codebase architectures.

• Stacked PRs allow teams to maintain rapid code review cadences without dropping context on large-scale refactors or multi-part feature builds.

• Automatic downstream rebasing eliminates tedious manual git mechanics when upstream PR feedback requires refactoring earlier commits.

• Managing dependency trees across pull requests moves AI developer tools significantly closer to matching senior human software engineering workflows.

// TAGS

devinaigithubstacked-prsdevtoolcode-reviewsoftware-engineering

DISCOVERED

1h ago

2026-07-30

PUBLISHED

1h ago

2026-07-30

RELEVANCE

8/ 10

AUTHOR

cognition

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL21m ago

Thinking Machines releases Inkling Small

Thinking Machines has released Inkling Small, its second AI model coming just two weeks after its predecessor. Operating with less than a third of the total and active parameters of the original flagship Inkling model, Inkling Small scores 40 on the Artificial Analysis Intelligence Index, landing within a single point of the flagship's benchmark performance.

UPDATE21m ago

Merge Gateway adds GPT-5.6 Luna and Terra models

Merge Gateway has expanded its model offerings by launching support for GPT-5.6 Luna and Terra on its platform. Developers and teams can now access these newly available models through Merge Gateway with an additional 15% promotional discount.

NEWS46m ago

Inception CTO details diffusion LLM token efficiency

Inception AI co-founder and CTO Aditya Grover will present "Redefining the Token Efficiency Frontier with Diffusion LLMs" at the Agentic AI Summit 2026 on August 1 at UC Berkeley. The session will cover emerging techniques for optimizing token efficiency using diffusion-based language model architectures.