Cursor (unofficial)
banner
cursor.mbdio.uk
Cursor (unofficial)
@cursor.mbdio.uk
The best way to code with AI.

unofficial account crossposting from Twitter - run by
@danielmorrisey.com
x.com/cursor_ai
Cursor can now use past conversations as context.
February 18, 2026 at 8:45 PM
Sonnet 4.6 is now available in Cursor.

Our benchmarks show it as a notable improvement over Sonnet 4.5 on longer tasks, but below Opus 4.6 for intelligence.
February 17, 2026 at 7:30 PM
Extend Cursor with plugins, now available in our marketplace.
February 17, 2026 at 6:45 PM
Long-running agents are now available at http://cursor.com/agents for Ultra, Teams, and Enterprise plans.

With our new harness, agents can complete much larger tasks.

http://cursor.com/blog/long-running-agents
February 17, 2026 at 2:33 PM
We've raised limits for Auto and Composer 1.5 for all individual plans.

Individual plans now have 3x usage of Composer 1.5 versus Composer 1. For a limited time (through February 16), we're increasing that to 6x.
February 17, 2026 at 2:32 PM
Composer 1.5 is now available.

We’ve found it to strike a strong balance between intelligence and speed.
February 17, 2026 at 2:32 PM
GPT-5.3 Codex is now available in Cursor!

It's noticeably faster than 5.2 and is now the preferred model for many of our engineers.
February 17, 2026 at 2:31 PM
Opus 4.6 (fast mode) is now available in Cursor!

It's 2.5x as fast in research preview.
February 17, 2026 at 2:31 PM
Opus 4.6 is now available in Cursor!

It's highly effective at long-running tasks and reviewing code.
February 17, 2026 at 2:31 PM
We've been working on very long-running coding agents.

In a recent week-long run, our system peaked at over 1,000 commits per hour across hundreds of agents.

We're sharing our findings and an early research preview inside Cursor.
February 17, 2026 at 2:30 PM
We're proposing an open standard for tracing agent conversations to the code they generate. It's interoperable with any coding agent or interface.

https://agent-trace.dev
Agent Trace
A standard format for tracking AI-generated code.
agent-trace.dev
February 17, 2026 at 2:30 PM
Semantic search significantly improves coding agent performance.

For very large codebases, Cursor's indexing process is now several orders of magnitude faster.

http://cursor.com/blog/secure-codebase-indexing
Securely indexing large codebases · Cursor
By securely reusing a teammate's existing index, we cut time-to-first-query from hours to seconds on the largest repos.
cursor.com
February 17, 2026 at 2:30 PM
Cursor can now use multiple browsers at once with subagents.
February 17, 2026 at 2:30 PM