Features
Autonomous feedback loop: resume agent on CI failures, merge conflicts, review requests
Seven-stage pipeline: intake, queued, provisioning, running, PR opened, CI & review, merged
Multi-agent support: Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, OpenCode
Pod-per-repo isolation with concurrent git worktree execution
Agent workflows: reusable, parameterized jobs with schedule or webhook triggers
Connections: external tool access for agents (Notion, Slack, Linear, GitHub, PostgreSQL, Sentry)
Intake from GitHub Issues, GitLab Issues, Linear, Jira, Notion, or manual
Scheduled tasks with cron triggers
Webhook triggers for external event-driven tasks
Standalone agent tasks without git checkout (reports, triage, automations)
Real-time dashboard with live log streaming, pipeline visualization, cost analytics, cluster health monitoring
Self-healing pipeline: auto-resume on failures, auto-merge on CI+review pass, auto-close issues
Custom MCP server and HTTP API connection support
Helm chart for Kubernetes deployment
Fastify API, Next.js dashboard, BullMQ workers, Drizzle on Postgres
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
