lavra
Persistent memory, structured planning, and multi-agent code review
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install Lavra?โผ
Run `npx skills add roberto-mello/lavra --all -g -y` in your terminal to install all skills globally. Lavra also requires the beads CLI, jq, and sqlite3.
What does Lavra do for coding agents?โผ
It adds persistent memory, structured planning, multi-agent code review, and one-command shipping so your coding agent gets smarter with every task instead of forgetting everything between sessions.
How does Lavra's memory system work?โผ
Knowledge like decisions, fixes, and patterns is captured inline during work into a git-tracked knowledge.jsonl file, then automatically recalled at the start of every session based on your current tasks.
Does Lavra work with Claude Code, OpenCode, and Gemini CLI?โผ
Yes. Lavra supports Claude Code, OpenCode, Gemini CLI, and Cortex Code, with full hook compatibility across platforms.
Can non-developers use Lavra?โผ
Yes. Commands like /lavra-design and /lavra-work handle brainstorming, planning, and implementation with built-in quality gates, so you describe what you want in plain English.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core