lavern

Grade A: derived only from the two verdicts below. How grades work

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.

SteadyCurrent depsChecked Oct 19, 2026Free

Visit lavern ↗Source on GitHub ↗

Why this verdict

How we check →

15 commits in the last 90 days, none in the last 30. receipt ↗
Latest release v0.15.0, 155 days ago. receipt ↗
On current major: Zod. receipt ↗
Not counted in verdict: Stripe SDK 20 → 23, TypeScript 6 → 7. receipt ↗

Snapshot: commit 526a3b8 on main, checked 2026-10-19 07:15 UTC. Receipts link to files at this exact commit.

Dependency freshness

Package	Declared	Latest	Status
Stripe SDK stripe	20.4.1	23.0.0	Behind, not counted
TypeScript typescript	6.0.3	7.0.2	Behind, not counted
Zod zod	4.0.0	4.6.7	Current

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Payments: Stripe
Database / ORM: SQLite
Email: Resend
AI: OpenAI SDK, Anthropic SDK
Testing: Vitest

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

AI
67 agent prompts67 agent prompts: 59 specialists, 7 workflow-specific orchestrators
AI
9 workflows9 workflows from a single-specialist counsel call to a full adversarial review
AI
3 inference providers3 inference providers: Anthropic Claude (US), Mistral AI (EU), or local via Ollama
AI
Three-layer verificationEvaluator gate (drops weak findings) → adversarial debate (red team / blue team) → 10-pass verification pipeline
AI
Human gatesCritical findings don't auto-deliver. The orchestrator surfaces the call and waits for a human to approve or override.
AI
Precedent Board memoryPersistent memory across engagements. Findings that recur across documents get reinforced; stale ones decay.
API
21 MCP tools21 MCP tools for debate, scoring, verification, grounding, memory, knowledge base, quality checks
API
Session and engagement APIPOST /api/sessions | Create analysis session
Auth
Local single-user modeOut of the box Lavern runs single-user on your machine. No login, no signup, no cookies.
Data
5 seeded legal datasets5 seeded legal datasets: CUAD, MAUD, ACORD, UNFAIR-ToS, LEDGAR
Testing
1,677 tests1,677 tests across 105 files
UI
React dashboardReact SPA, editorial design language (Newsreader serif, Geist sans, cream paper). WCAG AA accessible

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote; 2 unverifiable items were discarded. A README claim is the maker's description, not something we tested.

Watch lavern

Get told if it goes dormant, gets archived, falls further behind on a core dependency, or changes its license or price.

RSS feed for lavern · all changes

History

Sep 29, 2026 → Oct 19, 2026. One square per check, colored by maintenance status. Hover for details.

Show as a table

Date	Maintenance	Dependencies	Commits (90d)
Oct 19, 2026	Steady	Current deps	15
Oct 12, 2026	Steady	Current deps	15
Sep 29, 2026	Active	Current deps	20

Sources

Every claim on this page comes from these public records, checked Oct 19, 2026. Open them to verify.

Commit history ↗ default branch (main) at the checked commit: pulse, contributors, last commit
Releases ↗ latest release
package.json ↗ declared dependency versions and stack (at commit 526a3b8)
README ↗ quoted features at the checked commit
npm registry ↗ latest versions (each linked in the table above)

Maintainer? Add the badge

It updates automatically every time we refresh the evidence. Clicking it opens this page.

[![kitproof](https://kitproof.dev/badge/lavern.svg)](https://kitproof.dev/kits/lavern/)