# Joshua Saxe

> Joshua Saxe is llamaFirewall research coauthor; former Meta security AI leader. LlamaFirewall on Anchor Terminal, with grades, an about and public profiles.

- Canonical: https://www.anchorterminal.com/people/joshua-saxe/
- Markdown: https://www.anchorterminal.com/people/joshua-saxe/index.md (~950 tokens)
- Slim: https://www.anchorterminal.com/people/joshua-saxe/index.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/people/joshua-saxe/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-27

LlamaFirewall research coauthor; former Meta security AI leader.

- X: https://x.com/joshua_saxe

## What Joshua builds

- [LlamaFirewall](https://www.anchorterminal.com/tools/llamafirewall.md), graded D, 51.1/100, in Guardrails & safety filters. LlamaFirewall is Meta's open-source Python library for screening an AI agent's inputs, tool results and outputs. It runs scanners for prompt injection, hidden characters, insecure generated code and goal drift, and returns allow, block or human review. LlamaFirewall research coauthor; former Meta security AI leader, researched 2026-10-27.

## Works with

- [Abraham Montilla](https://www.anchorterminal.com/people/abraham-montilla/), Llama Guard 4 release/model-card contributor (GitHub amontilla0)
- [Connor Treacy](https://www.anchorterminal.com/people/connor-treacy/), Meta Product Manager; Meta Model API launch-guide co-author
- [Josh Walters](https://www.anchorterminal.com/people/josh-walters/), Developer marketing; Meta Model API launch-guide co-author
- [Mahesh Pasupuleti](https://www.anchorterminal.com/people/mahesh-pasupuleti/), Senior Engineering Leader, Meta Superintelligence Labs, AI Safety and Alignment; led Llama Guard development
- [Mark Zuckerberg](https://www.anchorterminal.com/people/mark-zuckerberg/), Founder, Meta
- [Sahana Chennabasappa](https://www.anchorterminal.com/people/sahana-chennabasappa/), AI Security Engineer; LlamaFirewall paper first-listed author
- [Tatiana Shavrina](https://www.anchorterminal.com/people/tatiana-shavrina/), AI/ML Research Lead; Muse Glimmer research team

## Questions

### Who is Joshua Saxe?

Joshua Saxe is llamaFirewall research coauthor; former Meta security AI leader.

### What does Meta make?

Anchor Terminal lists LlamaFirewall from Meta. LlamaFirewall is Meta's open-source Python library for screening an AI agent's inputs, tool results and outputs. It runs scanners for prompt injection, hidden characters, insecure generated code and goal drift, and returns allow, block or human review.

### How are Joshua's tools graded?

LlamaFirewall is graded D, 51.1 out of 100, on Anchor Terminal's benchmark, which scores every listing against the same checklist.

## Sources

- https://ai.meta.com/research/publications/llamafirewall-an-open-source-guardrail-system-for-building-secure-ai-agents/
- https://www.linkedin.com/in/sahana-chennabasappa-69a77576
- https://x.com/joshua_saxe
- https://dev.meta.ai/
- https://github.com/meta-llama/PurpleLlama/blob/main/CONTRIBUTING.md
- https://github.com/meta-llama/PurpleLlama/tree/main/LlamaFirewall

These are the people building the tools we list, named for their public role in the company or project behind a listing, from public pages, with the date it was researched. They don't work for Anchor Terminal (our own team is on the about page, /about/#author). We show public roles, public profiles and what the listing pages show, nothing private. To correct something, send an about or a photo, or have a page removed, write to privacy@anchorterminal.com.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp