Popular repositories Loading
-
agent-security-review
agent-security-review PublicOpen ast-grep rule pack for scanning AI-agent code. Grounded in Meta Rule of Two, CaMeL, MAESTRO, and the Lethal Trifecta; organized around Scope / Sign / Stop. Pulled live so the checks stay current.
-
mcp-oauth-sample
mcp-oauth-sample PublicOAuth 2.1 authorization and MCP server on Vercel for MCP clients with real-time analytics and threat detection
HTML 4
-
-
GrayZoneBench
GrayZoneBench PublicOpen-source AI safety benchmark testing how models handle tricky gray-zone requests. CLI for running benchmarks + web dashboard for exploring results.
Python 1
Repositories
- decision-models-as-guardrails Public
Can a decision model replace your guardrail? Open benchmark of 19 systems (Jev, Clef, Strands Deciders, the Perplexity and OpenAI Decisions APIs, Bedrock Guardrails) on the same 9,975 checks, scored on accuracy and cost.
- raxit-engine-releases Public
- dogwood Public Forked from dogwood-policy/dogwood
Reference parser and interpreter for the Dogwood policy language
- agent-security-review Public
Open ast-grep rule pack for scanning AI-agent code. Grounded in Meta Rule of Two, CaMeL, MAESTRO, and the Lethal Trifecta; organized around Scope / Sign / Stop. Pulled live so the checks stay current.
- DirePhish Public
Incident Response Simulation Engine - Multi-agent swarm intelligence for IR tabletop exercises
- nla-audit Public
An experiment in monitoring what LLMs are thinking. Current implementation reads activation-level thoughts via Anthropic's Natural Language Autoencoder release.
- mcp-oauth-sample Public
OAuth 2.1 authorization and MCP server on Vercel for MCP clients with real-time analytics and threat detection
- gpt-oss-safeguard-testing Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…