Features
Scans past Cursor and Claude Code sessions
Extracts bugs, fixes, design decisions, and gotchas
Automatic context loading via MCP at session start
Zero-config setup in Claude Code
Single static binary, no runtime dependencies
Multi-backend LLM routing (Claude CLI, Anthropic API, OpenAI, NVIDIA)
Stable project IDs derived from git remote URLs
Local-first with opt-in cloud sync
Secret redaction before LLM processing and cloud sync
System keychain storage for API keys
Unlimited insights on paid plan
Supports Claude Code, Cursor, Windsurf, Kiro
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
