MCP policy proxy for AI agents: hard spend limits, destructive-action approvals, kill switch, scoped keys, dry-run diffs, loop breaker, hash-chained audit log.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/agentwares/agentguard && cp agentguard/*.md ~/.claude/agents/Subagents overview
# agentguard A policy proxy between an AI agent and the tools it can reach: hard spend limits, approval before anything destructive, a kill switch, per-agent scoped credentials, dry-run writes with a mutation diff, a semantic loop breaker, and a hash-chained audit log you can verify. ```bash npx @agentwares/agentguard init ``` No LLM calls anywhere in it. No phone-home. No account. MIT. - `packages/agentguard-core` — the policy engine (Web-standard, runs anywhere) - `apps/agentguard-cli` — `agentguard`, the proxy and its commands - `packages/agentguard-sdk` — the same engine for non-MCP tool calls - `assets/permission-diff-action` — a GitHub Action that comments when agent permissions widen - `packages/mcp-kit`, `packages/notify`, `packages/x402` — generic plumbing the CLI bundles Hosted incident dashboard, audit retention and alerting: https://agentwares-agentguard.vercel.app This repository is exported from a private monorepo, which is why it has no long history. The exported source is complete and is exactly what is published to npm.
What people ask about agentguard
What is agentwares/agentguard?
+
agentwares/agentguard is subagents for the Claude AI ecosystem. MCP policy proxy for AI agents: hard spend limits, destructive-action approvals, kill switch, scoped keys, dry-run diffs, loop breaker, hash-chained audit log. It has 0 GitHub stars and its last recorded update is dated 2026-09-07.
How do I install agentguard?
+
You can install agentguard by cloning the repository (https://github.com/agentwares/agentguard) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is agentwares/agentguard safe to use?
+
Our security agent has analyzed agentwares/agentguard and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains agentwares/agentguard?
+
agentwares/agentguard is maintained by agentwares. The last recorded GitHub activity is dated 2026-09-07, with 0 open issues.
Are there alternatives to agentguard?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy agentguard to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/agentwares-agentguard)<a href="https://claudewave.com/repo/agentwares-agentguard"><img src="https://claudewave.com/api/badge/agentwares-agentguard" alt="Featured on ClaudeWave: agentwares/agentguard" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.