Features
Local-first execution: code never leaves your machine
Bring your own LLM key (OpenAI, Anthropic, any OpenAI-compatible endpoint)
Autonomous harness scaffolding and self-optimization in real time
Multiple interaction modes: Ask, Plan, Coding, Freestyle, Harness, CoWork
In-place file editing with diff review and checkpoint rewind
Interactive terminal and file explorer within the desktop app
MCP server support (stdio, streamable HTTP, SSE)
Voice API integration: TTS, STT, and voice-to-voice
CoWork mode for GUI/OS automation (clicking, typing, emailing)
Graph-aware code search via optional Context Engine
Persistent memory store (ResearchSwarm bridge) for compounding knowledge
Interactive terminal and session history
Rust-based for performance and low resource usage
Native desktop app (no web interface)
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
