Pinned Loading

1. start-here start-here Public

   Michael Saleme - Agent Security Research & Governance. 3 DOIs, 342 tests, NIST engaged.

2. red-team-blue-team-agent-fabric red-team-blue-team-agent-fabric Public

   342-test security harness for autonomous AI agents. MCP, A2A, x402/L402, AIUC-1 pre-cert, NIST AI 800-2 aligned. 97.9% HRAO-E validated. pip install agent-security-harness

   Python 6 2

3. ChatMeld-Ollama ChatMeld-Ollama Public archive

   Privacy-focused multi-LLM chat app with Ollama support for local AI models (Qwen, Llama, Mistral). Fork of ChatMeld.

   TypeScript 4

4. ace-experiment-framework ace-experiment-framework Public archive

   Boundary-discovery and anti-self-deception framework for AI efficiency research. Produces falsifiable, condition-specific verdicts. First validated result: a hard failure boundary for token pruning.

   Python

5. aiuc1-readiness aiuc1-readiness Public archive

   AIUC-1 Readiness Assessment - Pre-certification adversarial testing for AI agents

   HTML

6. awesome-mcp-security awesome-mcp-security Public

   Forked from Puliczek/awesome-mcp-security

   🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️