GitHub · Python
mcpware/IntentProbe
CPU activation probes for AI-agent guardrails and classification. One frozen local model pass, many independent heads. Open models, code and reproducible benchmarks.
- Stars
- 9
- Forks
- 0
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: activation-probing, ai-agent-security, claude-code, interpretability, mcp, mcp-security, open-source, tool-poisoning, agent-security, guardrails
Latest data point: Nov 20, 2026 · 9 stars · 0 forks