Features
Run AI coding agents in isolated sandboxed environments
Unified API to swap between Claude Code, Codex, OpenCode without code changes
Multi-repo support: agents can reason across frontend, backend, workers, infra, shared packages
Full infrastructure: install packages, run Docker, seed databases, start dev servers, execute tests
Warm dev environment: repo cloned, dependencies installed, services running before task starts
Support for any model: route hard tasks to frontier models, routine work to open-source models (Qwen, Kimi, GLM)
Event-driven triggers: GitHub PR, Slack message, Linear issue spin up isolated agent instance
Automation of recurring tasks: triage incidents, check cloud resources, update docs, follow up on issues
MCP server support for custom workflow integrations
Open-source TypeScript SDK on GitHub
Bring your own API keys (on Pro, Max, Enterprise)
Larger machines available on Max and Enterprise plans
Private cloud deployment in your VPC (Enterprise)
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
