io.github.mdfifty50-boop/agent-guardai

agent-guard

Verified · 2 mo ago

Constitutional guardrails and loop detection for AI agents

Install

claude mcp add agent-guard -- npx -y [email protected]

Our take

Adds defensive controls for AI agents, especially constitutional guardrails and loop detection. It is for teams running autonomous or semi-autonomous agents that need a basic safety layer around tool use and execution flow. The problem it addresses is real, but the implementation looks early and should be tested carefully because guardrail tools can fail in subtle ways.

reviewed by hand · 2026-07-17

Something wrong or dead here? Report it

Verification record

last verified
2 mo ago
github stars
0
last commit
7 mo ago
archived
no
latest version
0.1.3
in registry since
2026-04-24

github.com/mdfifty50-boop/agent-guard-mcp

reaai

REA

Verified · 33 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 33 days ago

rufloai

Ruflo

Verified · 9 days ago

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

hand-reviewed81k stars72k dl/wkchecked 9 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 2 mo ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 2 mo ago

openseoai

OpenSEO

Verified · 5 days ago

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

hand-reviewed28k starschecked 5 days ago