Features
Parallel task execution in isolated cloud sandboxes
Powered by codex-1 (OpenAI o3 optimized for SWE)
Reinforcement learning for clean, human-like patches
Real-time progress monitoring with citations and logs
Iterative test execution until passing
AGENTS.md file support for project guidance
Automatic code commit after task completion
User-configurable environment matching dev setup
GitHub pull request proposal
Read and edit files, run commands (test, lint, typecheck)
Optional internet access (enabled June 2025)
Secure isolated containers (internet disabled by default)
Task completion in 1-30 minutes
Verifiable evidence of actions (citations, terminal logs, test outputs)
192k token context length at medium reasoning effort
Autonomous vulnerability scanning and PR generation
PR review for quality, security, and best practices
Legacy COBOL to Java migration with testing
Incident triage and root cause analysis
Agent Canvas: manage multiple agents in one workspace
Cloud agents run even when your machine is off
Schedule recurring tasks via cron or event triggers
Trigger workflows from GitHub, Slack, PagerDuty
Model-agnostic: supports Claude Code, Codex, Gemini CLI, MiniMax M2.7
Isolated sandbox execution on VM or cloud
Fine-grained access control and budget guardrails
Audit trails for enterprise compliance
Self-hosted deployment in your VPC
Open-source SDK for custom agent development
In-chat model switching with saved LLM profiles
