Features
Launch multiple AI coding agents side by side (Claude Code, Codex CLI, Gemini CLI, etc.)
API Bridge to switch model providers without per-agent config changes
Remote session control from messaging apps (Telegram, Slack, Discord, WeChat, DingTalk)
Web Hub for browser-based agent management and previews
Web Terminal with PTY/tmux sessions and authenticated dev-server previews
Session handover: continue work from phone, messaging, or desktop seamlessly
Agent profile launcher: save and run profiles with specific agents and models
Local-first architecture with opt-in tunnels for remote access
CLI interface with 'va serve', 'va tui', and 'va launch' commands
Support for first-party and OpenAI-compatible API endpoints
Desktop app for macOS (Apple Silicon), Windows (x64), Linux (x64)
npm CLI package for terminal-first workflows
Unified workspace for coordinating agents and sessions
Agent teams with three modes (side by side, team, etc.)
Open source (source, issues, and release notes on GitHub)
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
