Features
PRD-driven loop generation from raw requirements
Per-task specification with detailed steps for hundreds of tasks
Deterministic Docker sandbox per agent (ralph-<agent>-<dir>-<hash>)
Multi-agent support: Claude, Codex, Cursor, Copilot, Gemini, opencode
Live step detection and stream preview
Screenshot capture during execution
Full history logs with per-iteration timing
Mid-flight steering by editing .agent/STEERING.md
Automatic commit after loop completion for review
Network policy allowlisting for sandbox (sbx policy)
YOLO mode (--dangerously-skip-permissions) for full shell access
Sandbox debugging via sbx exec to reproduce failures
Iterates through task list until completion
CLI-based interface (no web UI)
Open-source (MIT license)
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
