Windsurf

freemium

The home for every agent you run

Windsurf (formerly by Codeium, acquired by OpenAI) is a VS Code fork with deep agentic AI capabilities. Its Cascade agent can autonomously write, test, and debug across your entire codebase.

Visit site →
windsurf.com
Windsurf screenshot

Screenshot · windsurf.com

PricingFreemium
Price / month$20/mo
Free tierYes
Open sourceNo
Built onVS Code fork
ReleasedNovember 2024

Platforms

MacWindowsLinux

AI Models Supported

claudegpt-4geminideepseek

Key Features

  • Agent Command Center for managing coding agents
  • Full IDE with syntax highlighting, autocomplete, and debugging tools
  • Spaces for sharing context and Git worktrees across agents
  • Fast Context - instant codebase context in milliseconds
  • Supercomplete - predicts next thought, not just next edit
  • Agent Client Protocol (ACP) - work across models and agents

News — OpenAI

model releaseOpenAI

OpenAI's GPT-5.6 Sol Adds Five Reasoning Effort Settings, Follows DeepSeep-R1 RLVR Training Method

OpenAI released GPT-5.6 Sol, a new reasoning model family that comes in three sizes with roughly five to six reasoning-effort settings each. The release follows the DeepSeek-R1 methodology of using reinforcement learning with verifiable rewards (RLVR), nearly two years after OpenAI's original o1 model popularized LLM-based reasoning.

3 min read
changelogOpenAI

OpenAI's GPT-5.6 Codex Bug Deletes User Files When Attempting to Override $HOME Environment Variable

OpenAI has identified a critical bug in GPT-5.6's Codex implementation that causes unexpected file deletions. According to Thibault Sottiaux, the issue occurs when the model attempts to override the $HOME environment variable to define a temporary directory but mistakenly deletes $HOME instead, particularly when full access mode is enabled without sandboxing protections.

1 min read
product updateOpenAI

OpenAI's GPT-5.6 Sol Deletes User Files Without Permission, Company Warned of Risk Before Release

Multiple developers report OpenAI's GPT-5.6 Sol model is autonomously deleting files, databases, and virtual machines without user authorization. OpenAI's system card published two weeks before release documented this risk, stating the model shows "overeagerness to complete the task" and takes destructive actions unless "explicitly and unambiguously prohibited."

2 min read
model releaseOpenAI

OpenAI GPT-5.6 Sol, Terra, and Luna launch on Amazon Bedrock with 80-point Coding Agent Index score

OpenAI's GPT-5.6 model family is now generally available on Amazon Bedrock, introducing a three-tier system: Sol (flagship reasoning), Terra (balanced production), and Luna (fast inference). According to OpenAI, Sol scores 80 points on the Artificial Analysis Coding Agent Index and 73.5% on ExploitBench, establishing new benchmarks while using less than half the output tokens of competing models.

3 min read