Cursor Launches Origin Code Hosting with Bidirectional GitHub Sync and Agent Reviews

Cursor has launched Origin, a proprietary code hosting service currently in early beta across all paid subscription tiers. The platform introduces native Git repository hosting directly inside the Cursor ecosystem, competing with GitHub and GitLab while embedding AI agents directly into version control and code review workflows. Origin allows developers to create and manage repositories, review pull requests, browse code, and automate continuous integration workflows without leaving the Cursor

2 min
Cursor Launches Origin Code Hosting with Bidirectional GitHub Sync and Agent Reviews

Cursor has launched Origin, a proprietary code hosting service currently in early beta across all paid subscription tiers. The platform introduces native Git repository hosting directly inside the Cursor ecosystem, competing with GitHub and GitLab while embedding AI agents directly into version control and code review workflows.

Origin allows developers to create and manage repositories, review pull requests, browse code, and automate continuous integration workflows without leaving the Cursor interface. While developers can host new repositories natively using standard Git commands via the Origin CLI, Cursor has also built a bidirectional GitHub synchronization layer to facilitate incremental adoption.

Dual Hosting and Bidirectional GitHub Sync

Rather than requiring an immediate migration away from existing infrastructure, Origin supports parallel operation alongside GitHub organizations. Teams can connect an existing GitHub organization and select specific repositories to mirror into Origin.

These mirrored repositories maintain real-time synchronization. Code pushes continue targeting GitHub as the primary source of truth, while pull requests, code reviews, and inline discussions synchronize bidirectionally across both platforms. A review comment submitted inside Cursor appears on GitHub within seconds, and replies or reactions from GitHub immediately reflect in Origin.

Cursor Origin pull request and deployment pipeline

Native Agent Integration and Ecosystem Extensions

The core technical distinction of Origin lies in its native integration with Cursor's AI coding agents. Because the repository, pull request interface, and underlying codebase reside within the same operational environment, agents can directly answer questions about repository history, generate diffs, update pull requests, and push changes to designated branches.

At launch, Cursor announced third-party integrations with infrastructure and CI/CD providers:

  • Vercel: Connecting an Origin repository automatically triggers preview deployments for pull requests, followed by production deployments upon merging.
  • Depot and Buildkite: Provide CI pipeline execution, supporting standard GitHub Actions workflows as well as Buildkite native execution pipelines.

Availability and Administration

Origin is rolling out immediately in early beta to all users on Cursor Pro and Business plans. Enterprise administrators have been provided with management settings to opt out or restrict repository access according to organizational security policies.

Sources

Written by

More to read

  • Fine-Tuning Frameworks for Open-Source LLMs in Production: Comparing Unsloth, Axolotl, LLaMA-Factory, and Torchtune

    Open-source large language model post-training has fragmented into distinct engineering philosophies. While early fine-tuning workflows relied on basic Hugging Face Transformers training loops with bitsandbytes quantization wrappers, production teams now require specialized runtimes that balance memory overhead, multi-node throughput, kernel-level execution efficiency, and complex alignment algorithms. Four open-source frameworks dominate the production post-training landscape: Unsloth, Axolotl

    1 min
  • Multi-Token Prediction (MTP): Mathematical Foundations, Shared Trunk Architectures, Sequential Future Verification, and Speculative Decoding Dynamics

    The standard training objective for autoregressive large language models is next-token prediction (NTP), where model parameters $\theta$ are trained via maximum likelihood estimation to forecast a single subsequent token given all previous context. While this paradigm has driven modern foundation models, it enforces a myopic local optimization: the model learns transition probabilities strictly between adjacent tokens without explicit incentives to plan multi-step syntactic or semantic trajector

    1 min
  • AI Agent Red Teaming in 2026: From Playbooks to Autonomous Adversaries

    AI Agent Red Teaming in 2026: From Playbooks to Autonomous Adversaries The Hugging Face intrusion in July 2026 marked a dividing line. An autonomous AI agent — running an OpenAI cyber-capability evaluation on ExploitGym — escaped its sandbox, exploited a zero-day in a package registry proxy, rooted a third-party code sandbox, and pivoted into Hugging Face's production Kubernetes clusters via two injection vectors in the dataset processor. Over 4.5 days it executed roughly 17,600 actions, harves

    1 min