Anthropic Just Open-Sourced All of Legal AI (70 Agents, Free)

Anthropic Just Open-Sourced All of Legal AI (70 Agents, Free)

Bitwise AI ~5 min Watch on YouTube ↗

Overview

Anthropic released Claude for Legal — a single Apache 2.0 GitHub repository containing 13 vertical plugins, 70+ named agents, and 30+ MCP connectors covering every major legal practice area. With a built-in Westlaw connector maintained by Thomson Reuters and output formats native to lawyers (Word tracked changes, multi-sheet Excel), this isn't a SaaS product — it's a free scaffold that commoditizes the multi-billion-dollar legal AI market and templates a pattern for every regulated vertical that follows.

1 The Market Disruption ▶ 0:00

Legal AI is a multi-billion-dollar category. Companies like Harvey, Habia, Spellbook, and CoCounsel sell six-figure subscriptions for contract redlining, case summarization, and model prompting. Harvey alone has 60+ Am Law 100 firms on contract.

Key insight: "Legal AI is a multi-billion-dollar category. That market just got a free reference implementation from Anthropic with Westlaw access included."

2 What's Inside — 13 Verticals, 70+ Agents ▶ 0:45

The repository maps directly to the legal practice landscape with 13 vertical plugins covering every major area of law.

3 The Thomson Reuters Play — Westlaw Goes Free ▶ 1:36

The move the legal tech industry didn't see coming: Thomson Reuters, the company that owns Westlaw, builds and maintains the CoCounsel legal MCP connector — and it's distributed through Anthropic's marketplace for free.

Key insight: "The biggest legal data moat in the industry, distributed through Anthropic's marketplace, for free."

4 The Cold Start Interview Pattern ▶ 2:04

Every plugin's first command is a cold start interview — a pattern developers should steal for any vertical AI deployment.

Key insight: "The model isn't the differentiator anymore. The output format is. Read the room — Anthropic did."

5 Security — Legal Builder Hub and Four Gates ▶ 2:54

Community skills flow through the Legal Builder Hub, where every inbound skill must pass four security gates.

6 Anthropic's Real Strategy — Win the Infrastructure ▶ 3:23

Why ship this for free? Because Anthropic isn't trying to win the legal app — they're trying to win the legal infrastructure.

Key insight: "The legal app layer is now a commodity. The model and the agent runtime — that's where Anthropic gets paid."

7 Four Patterns to Steal ▶ 4:18

The video closes with four architectural patterns from the repo that apply to any vertical AI deployment — not just legal.

  1. Skills as markdown files — greppable, reviewable, forkable. No compiled artifacts, no build steps.
  2. Claude.md as practice profile — one file that every skill reads from. The cold start interview writes it, all downstream skills consume it.
  3. MCP for tools — vendor-neutral plumbing. Swap data sources without changing skills.
  4. Dual deploy — same skill works as a plugin or a managed agent. Pick where it runs.
Key insight: "Anthropic just templated vertical AI. Medical, finance, ops — every one of those gets this pattern next."

🎯 Key Takeaways

  1. 70+ free legal AI agents — Anthropic released anthropic/claudeforlegal under Apache 2.0, covering 13 practice areas with 30+ MCP connectors pre-wired.
  2. Westlaw access for free — Thomson Reuters maintains the CoCounsel MCP connector with verified citations across three jurisdictions, distributed through Anthropic's marketplace at no cost.
  3. Skills are just markdown — no build step, no compiled artifacts. The entire product is readable with cat. This makes it greppable, reviewable, and forkable.
  4. Cold start interview pattern — every plugin interviews the user to create a customized Claude.md practice profile. All downstream skills read from this one file. Steal this pattern.
  5. Output format is the differentiator — Word tracked changes, multi-sheet Excel with sources tabs. Anthropic understood that lawyers live in .docx, not VS Code.
  6. Four security gates — hidden content scan, prompt injection detection, restrictive allow list, rescan on update. Non-lawyers get routed to attorneys, not "install anyway" buttons.
  7. Dual deploy architecture — same skill runs as a Claude Co-Work plugin or a managed agent API behind your own orchestrator. One source, two runtimes.
  8. The app layer is now commodity — Anthropic's play isn't the legal app, it's the infrastructure. The model and agent runtime are where they get paid.
  9. Augmentation, not replacement — every output is a draft for attorney review. Source attribution, conservative privilege defaults, jurisdiction surfacing, and explicit send gates are baked in.
  10. This templates every vertical — medical, finance, ops. The four patterns (markdown skills, practice profiles, MCP tools, dual deploy) apply to any regulated industry.

⏱ Timestamp Index

▶ 0:00 The market disruption — free legal AI
▶ 0:45 Inside the repo — 13 verticals, 70+ agents
▶ 1:10 Practice areas and law student plugin
▶ 1:36 Thomson Reuters and the Westlaw connector
▶ 2:04 Cold start interview pattern
▶ 2:36 Output format — Word and Excel for lawyers
▶ 2:54 Legal Builder Hub — four security gates
▶ 3:23 Strategy — winning the infrastructure
▶ 3:53 Guardrails — augmentation, not replacement
▶ 4:18 Four patterns to steal for any vertical
▶ 4:44 What comes next — medical, finance, ops