MakerChecker: Open-Source Security Gateway for AI Agents with RBAC and Audit Logging
By
smashini
Summary
MakerChecker is an open-source security gateway and static scanner designed for AI agents. It enforces deny-by-default access control, role-based access control (RBAC), human-in-the-loop approvals, segregation of duties, and cryptographically signed, offline-verifiable audit logs. The tool sits between AI agents (running frameworks like LangChain, Claude SDK, or CrewAI) and their tool calls, acting as both a checkpoint and a signed ledger to ensure agents can only act within their granted roles and cannot approve their own work.
Source
Hacker NewsMakerChecker: Open-Source Security Gateway for AI Agents with RBAC and Audit Logginggithub.comKey quotes
· 3 pulledDeny-by-default enforcement, human approvals, and a cryptographically signed audit trail — so your agent runs only what it's granted and provably can't approve its own work.
MakerChecker sits in front of every tool call as a checkpoint and behind it as a signed ledger: an agent acts only through a role, runs only the skills it was granted, cannot exceed its limits, and cannot approve its own work.
Your agents keep running in their existing framework (LangChain, Claude SDK, CrewAI).
You might also wanna read
Trace-AI: Security Tool for Predicting and Preventing Supply-Chain Attacks in Open-Source Dependencies
Trace-AI is a security tool that predicts and prevents supply-chain attacks by analyzing open-source dependencies, registries, and maintaine
Product Hunt·8mo ago
LangSmith launches LLM Gateway private beta for AI agent governance with cost controls and PII redaction
LangSmith has launched an LLM Gateway in private beta, providing a runtime governance layer that sits between AI agents and LLM providers. I
langchain.com·13d ago
Digimarc launches provenance and verification tools for AI agent workflows
Digimarc has launched new provenance and verification infrastructure aimed at securing autonomous and AI-enabled enterprise workflows. As AI
helpnetsecurity.com·1mo ago
Credence-Pi: An OpenClaw Plugin for Cost-Effective and Secure AI Agent Governance
The article introduces credence-pi, an OpenClaw plugin and local daemon that creates an automated governance layer for AI agents. It optimiz
clawbeat.co·15d ago
LetMeCheck.ai: Code Quality Analysis Tool for Technical Leaders
LetMeCheck.ai is a code analysis tool that provides code quality insights for founders, CTOs, and tech leads to assess their codebase health
Product Hunt·1y ago
Cybercheck: The unproven AI crime detection tool used across the U.S. raises serious concerns
An investigative piece examining Cybercheck, a controversial AI-powered tool created by Nova Scotia entrepreneur Adam Mosher that claims to
cbc.ca·2d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.