repoGitHubTrust 82 · PrimaryPublished 9d agoLive · 7h ago
Vishisht16/Humane-Proxy
Lightweight AI safety middleware that protects humans by intercepting self-harm and criminal intent in LLM prompts. Features a 3-stage safety pipeline, MCP server for agents, and automated care responses.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Implements
Covers
Related to
Implements (incoming)
Related across the graph
newsOrca provides safety layer for autonomous AI agents - Let's Data SciencepaperWhen Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent SystemspaperBehind the Refusal: Determining Guardrail Activation via Behavioral MonitoringnewsNemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AInewsAI browsers can be lulled into a dream world where guardrails no longer applycompanyVerisight
