Features
Stateless agents with full message control
Composable middleware (turn tracking, retry, compaction, persistence)
Hierarchical subagents with background execution
Context compaction with two-phase pruning and LLM summarization
Tool permission callbacks with async approval
MCP integration via stdio, HTTP, or SSE
On-demand SKILL.md instruction loading
Automatic AGENTS.md/CLAUDE.md project context injection
Built-in filesystem and bash tools
TypeScript-first with full type safety
React and Vue integration hooks
Streaming support for CLI and web UIs
Works with any model provider via Vercel AI SDK
Open source under MIT license
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
