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.

语言：Python · GitHub 星标：9 · Fork：0

话题：activation-probe · activation-probing · agent-security · ai-agent-security · authorization · claude-code · cpu-inference · guardrails

在 GitHub 上查看原仓库