Features
Autocomplete predicts next code blocks in real-time
Agent Mode for autonomous task execution (write tests, refactor, create PRs)
Chat Mode for conversational code generation and debugging
Custom modes (e.g., security auditor, documentation generator)
Multi-language support (JavaScript, Python, Rust, etc.)
Terminal integration for command-line workflows
Local-first design: code never leaves your machine
Transparent, auditable suggestions with traceability
Project-wide context awareness (understands dependencies, structure, configs)
Docker and Kubernetes integration for deployment configs and debugging
Documentation generation from code context
Support for 23+ AI models from 6 providers (OpenAI, Anthropic, Google, Cohere, Mistral, OpenRouter)
Live browser preview from chat
Browser automation for testing and debugging UI
Screenshot analysis for catching UI issues
Live knowledge graph from code, commits, issues, and docs
Feasibility analysis: flags buildable vs risky items
Technical design document generation grounded in service topology
Impact assessment maps services, APIs, and dependencies across repos
Auto-scoping epics into Jira/Linear stories with effort estimates
One-shot production code generation grounded in service patterns
AI code reviews with cross-repo impact analysis
Production issue triage via MCP
Conversational learning from Slack and Jira
Accelerated onboarding via system-level Q&A in coding agents
Create Jira tickets and merge requests from Slack
MCP server for integration with Cursor, Claude Code, Codex
On-prem or cloud deployment
No code storage or model training
