Cursor has announced that its long-running agents research preview is now available to all Ultra, Teams, and Enterprise users, following internal and external testing. The feature is designed for developers and engineering teams seeking to automate complex, multi-hour or multi-day software tasks with less human oversight. Availability is currently limited to higher-tier customers, with public rollout details yet to be disclosed.
Long-running agents are now available at https://t.co/3PT8c7azU3 for Ultra, Teams, and Enterprise plans.
— Cursor (@cursor_ai) February 12, 2026
With our new harness, agents can complete much larger tasks.https://t.co/7p57WeR04t pic.twitter.com/pGePEFRPTT
The long-running agents leverage a custom-built harness that allows autonomous software agents to handle extended, intricate projects such as:
- Building integrated chat platforms
- Refactoring authentication systems
- Porting applications across platforms
Unlike previous agent iterations that struggled with long-horizon tasks, this system introduces a planning phase that requires user approval before execution, reducing errors caused by misalignment. The agents also use multiple models that verify each other's work, enabling the creation of large, production-ready pull requests with minimal manual follow-up.
Cursor, the company behind this release, has focused its recent R&D on agent autonomy and reliability, aiming to move toward fully self-driving codebases. The company’s adoption of a flexible harness enables integration with various AI models, tailoring agent behavior to each task's needs. Early feedback from users and industry engineers indicates substantial productivity gains, with some projects completed in a fraction of the originally estimated timeframes and codebases benefiting from deeper test coverage and better handling of edge cases.
