Features
Local autonomous coding agent that reads, writes, and fixes code
Multi-provider support: OpenAI, Claude, Gemini, Ollama, DeepSeek, Groq, Mistral, etc.
Block-based prompt editor for creating and managing prompt templates
Agentic flavours – custom agent configurations
Task tracker with step-by-step logging
Expert Mode for smarter model review and improved results
Visual diffs for code changes
Multi-project support with tabs
Bring Your Own Keys – no usage fees, only pay the model provider
Unsafe-mode flag for unrestricted file execution
Multiple themes: Light, Caramel Latte, Dark Coffee
Qwen3 model support via MLX on Mac
Three-slot model pipeline for combining models
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
