AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
lavern
lavern logo

lavern

Active·★ 315·Apache-2.0·Updated 2026-09-05

Lavern is a multi-agent legal system featuring 67 specialized agents and orchestrators that coordinate through a debate protocol to analyze legal documents. It reads documents, posts findings with cited evidence, runs three layers of verification, and pauses at human gates before critical decisions, supporting Anthropic, Mistral, or local Ollama LLMs.

lavern sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Comprehensive Multi-Agent System comprising 67 specialized agents and orchestrators.. A representative use case is Interactive legal document analysis with real-time agent activity feed and human approval.. The listed license is Apache-2.0. GitHub stars are currently 314. Relevant tags include Multi-Agent System, Legal AI.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#Multi-Agent System#Legal AI#LLM Orchestration#Agent Debate#Human-in-the-Loop#Document Analysis#Verification#Node.js
$ Install
$ curl -fsSL lavern.ai/install.sh | sh
↗ Visit site★ GitHub
01

Features

01Comprehensive Multi-Agent System comprising 67 specialized agents and orchestrators.
02Structured Debate Protocol enforcing evidence citation and allowing peer challenges among agents.
03Multi-Layer Verification with evaluator gates, adversarial debate, and a 10-pass quality assurance process.
04Human-in-the-Loop Decision-Making via human gates for approval or override of critical findings.
05Persistent Knowledge Base (Precedent Board) for accumulating and reinforcing findings across engagements.
02

Why choose it

+Comprehensive Multi-Agent System comprising 67 specialized agents and orchestrators.
+Structured Debate Protocol enforcing evidence citation and allowing peer challenges among agents.
+Interactive legal document analysis with real-time agent activity feed and human approval.
+Supports 7 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

macOS
Operating System
Verified via docs
Linux
Operating System
Verified via docs
Windows
Operating System
Verified via docs
Node.js
Runtime
Verified via docs
Anthropic
LLM Provider
Verified via docs
Mistral AI
LLM Provider
Verified via docs
05

Quick start

1
$ curl -fsSL lavern.ai/install.sh | sh
06

Use cases

↳Interactive legal document analysis with real-time agent activity feed and human approval.
↳Autonomous document monitoring and review (Clawern mode) with notification and precedent accumulation.
↳Developing and experimenting with advanced multi-agent architectures and debate protocols for various domains.
↳Automating legal research and the generation of evidenced findings for legal professionals.
↳Ensuring compliance and ethical processing in AI operations by leveraging EU-based providers and conservative risk postures.
07

Alternatives

⚡Top VS:
VScrypto-claude-desk★64→VSplan-cascade★132→VSAgenticOS★24→VScockpit-agent★26→
crypto-claude-desk logo
crypto-claude-desk★ 64
Multi-agent cryptocurrency intelligence system built with Claude Code. 6 AI agents, 66 MCP tools, Agent Teams, zero orchestration code.
VSCompare→
plan-cascade logo
plan-cascade★ 132
AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).
VSCompare→
AgenticOS logo
AgenticOS★ 24
An open-source, self-hostable AI operating system and development workspace. Powered by Electron and React 19, it features multi-agent orchestration, full Model Context Protocol (MCP) support, native filesystem access, and an extensible tool ecosystem for autonomous software development.
VSCompare→
cockpit-agent logo
cockpit-agent★ 26
面向智能座舱的云边协同 AI Agent:端侧毫秒级车控,云端声明式 Multi-Agent 与 Skill/DAG 编排,支持 S2S 实时语音、声纹多用户、视觉与 HMI;LLM 只负责理解与规划,VAL 负责确定性安全执行。
VSCompare→
ai-rotom logo
ai-rotom★ 22
Pokemon Champions battle advisor MCP server
VSCompare→
thread-keeper logo
thread-keeper★ 14
Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
VSCompare→
suede-creator-skills logo
suede-creator-skills★ 126
67 open-source Agent Skills for Claude Code and Codex: Full Send orchestration, A-F code review, AI evals, CI ship-gates, design, copy, SEO/AEO/GEO, app shipping, creator rights, and consumer recovery.
VSCompare→
AgentNexus-LangChain-FastAPI logo
AgentNexus-LangChain-FastAPI★ 51
Langchain FastAPI server
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
AnttiHero /
lavern
↗

An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 10-pass verification loop. Apache 2.0.

315Apache-2.0
Last commit1mo ago
StatusActive
CategoryMulti-Agent
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.