No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by roberto-mello · Agent Tool · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is lavra safe to install? View the security audit →
Lavra (/ˈla.vɾɐ/ — Portuguese for "harvest") Lavra turns your AI coding agent into a development team that gets smarter with every task. A plugin for coding agents that orchestrates the full development lifecycle -- from brainstorming to shipping -- while automatically capturing and recalling knowledge so each unit of work makes the next one easier. [](https://www.snowflake.com/en/product/features
| Stars | 52 |
| Forks | 2 |
| Language | Shell |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.1913669719907/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-27 |
| Created | 2026-02-08 |
| Platforms | claude-code, cli, gemini |
| Est. Tokens | ~953k |
These tools work well together with lavra for enhanced workflows:
Looking for a lavra alternative? If you're comparing lavra with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic S
Communication for AI agents: stable identity, durable mail and chat, and wake-up events across sessions, runti
Community-driven workflows for Antigravity AI. Like Claude Skills - reusable prompts and automation for AI cod
Self-improving Agent orchestrator for all knowledge work
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
[DEPRECATED] Superseded by systempromptio/systemprompt-template and systempromptio/systemprompt-core. MCP serv
Explore other popular agent tool tools:
lavra is A plugin with compound engineering workflows and memory for AI coding agents. It is categorized as a Agent Tool with 52 GitHub stars.
lavra is primarily written in Shell. It covers topics such as agents, ai, beads.
You can find installation instructions and usage details in the lavra GitHub repository at github.com/roberto-mello/lavra. The project has 52 stars and 2 forks, indicating an active community.
lavra is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to lavra on Agent Skills Hub include jat, aweb, antigravity-workflows. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: