Features
Semantic code search by meaning and structure
Cited results with exact file and line range
Multi-hop search across files in one pass
Research packets combining multiple questions
Impact analysis before editing shared symbols
Incremental re-indexing of uncommitted edits
Warm start in about one second
CLI with --json output mode
HTTP API endpoint for querying indexed repos
Watch mode for continuous sync
Diff search modes: changed, impacted, regression
Automatic indexing of GitHub repositories via URL
Indexing of local working tree including uncommitted files
Structural parsing for Go, Rust, Ruby (since March 2026)
Large monorepo handling with generated file exclusion
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
