Open sourcePython · ≈4.4k stars · NOASSERTION (per GitHub; components carry Llama Community and MIT licenses)
PurpleLlama
Tools to assess and improve LLM security
PurpleLlama is Meta's set of tools to assess and improve LLM security. The repo contains LlamaFirewall, the Llama Guard safeguards, Prompt Guard (protection against malicious prompts), Code Shield and the CybersecurityBenchmarks (CyberSecEval).
In research (1)
Oct 27, 2026 · Meta's Llama security tooling (Prompt Guard, LlamaFirewall): a classifier/firewall alternative to model-internal attention gating for the same open-weight Llama models.
Neighbours on the workbench
JavaScript · ≈292k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
JavaScript · ≈52k stars · MIT
cloudflare/security-audit-skill
Cloudflare's skill for multi-phase security audits with independently verified findings.
Maintained by cloudflare
Go · ≈49k stars · Apache-2.0
alibaba/open-code-review
Alibaba's hybrid deterministic-plus-agent code review CLI.
Maintained by Alibaba
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- meta-llamaOrganisation
Sources
Verified Oct 29, 2026