Features
Code map: live mapping of functions, files, dependencies with full call graph
MemDB: bi-temporal graph database where every record knows its validity period
Fleet coordination: agents announce intent, auto-merge safe overlaps, flag conflicts
Time travel: rewind to any past moment in milliseconds
MCP-native: uses Model Context Protocol for agent integration
Impact analysis: answer 'what will this break?' with 97.3% accuracy (self-reported)
Real-time agent awareness across the fleet
Sub-13ms query latency (self-reported)
8.4x faster indexing vs ArcadeDB (self-reported)
Auto-merges 90% of overlaps without human intervention
Built in Rust, runs on a laptop (16 MB at 100k records)
Integrates with Cursor, Claude Code, Codex, Hermes, VS Code, Windsurf
No LLM calls for memory or coordination
Graph traversal 12.1x faster vs ArcadeDB (self-reported)
Ingests 1,500 files in 1.5 seconds (self-reported)
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
