Features
Runs local copies of Claude Code, Codex, and OpenCode on your machine
Browser-based Workbench with PWA installable as desktop/mobile app
Push notifications when agent tasks complete or need input
Durable Agent Harness: cron scheduling, event-driven triggers (PR, CI, file, log), run inspection and cancellation
Global and per-project skill library shared across all agents
Powered by open askill toolchain
Secure Cloudflare Tunnel with no inbound ports
Voice-to-text input for mobile briefings
Per-channel routing: different agents per chat surface (e.g., #frontend→OpenCode, #backend→Claude Code)
Resumable isolated sessions across devices
Inline agent switching by prefixing messages with agent name
Interactive prompts with buttons and modals in chat apps
Show Pages: agents can present live web pages (flowcharts, diffs, dashboards) to users
OIDC authentication with RS256 tokens, JWKS published, local session verification
Supports Slack, Discord, Telegram, WeChat, and Lark/Feishu as chat surfaces
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
