Features
Context Builder analyzes project and selects relevant files/functions
Assembles dense context within model token limits
Works with Claude MAX, ChatGPT Plus, Gemini — no extra API costs
MCP server backend for Claude Code, Cursor, and Codex
Real-time context analysis and file discovery for agentic tools
Optimizes prompts to reduce token waste and improve AI output accuracy
Integrates with existing AI subscriptions without separate API keys
Open-source Community Edition available on GitHub (June 2026)
Provides context engineering for coding agents to plan with full picture
Helps navigate large codebases by focusing on relevant files only
CLI tool for batch-processing context
Web app interface for visual context building
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
