claude-flow
Verified · 2 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
humane-proxy
Verified · 14 days agoAI safety middleware — detects self-harm and criminal intent in LLM prompts.
Install
claude mcp add humane-proxy -- uvx humane-proxy
Our take
Acts as a safety middleware layer that screens prompts for self-harm and criminal-intent patterns before they reach downstream models or tools. It is for developers adding lightweight policy enforcement to LLM apps without building a full moderation stack from scratch. The purpose is clear, but safety filtering is high-stakes and hard to validate, so this should be treated as one control in a broader review process, not a complete solution.
Verification record
- 14 days ago
- 29
- 22 days ago
- no
- Apache-2.0
- 2026-07-06
More in ai
browse all →tldraw
Verified · 4 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 21 days agoCodebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 16 days agoOfficial OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
mobilerun
Verified · 5 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 20 days agoAI Agents Framework with Self Reflection and MCP support