helm-ai-kernel
★ 60
vs
ADR
★ 2.1k
helm-ai-kernel vs ADR
helm-ai-kernel: HELM AI Kernel acts as a fail-closed execution firewall, intercepting AI agent requests to enforce default-deny policies and quarantine unknown tools. It provides verifiable evidence through signed receipts and EvidencePacks for audit and tamper checks, ensuring secure and governed AI operations.; ADR: ADR (Agentic Detection and Response) is an open-source framework designed to secure AI agents utilizing the Model Context Protocol (MCP). It comprises an ADR Sensor for telemetry collection and an ADR Detector, which serves as a dual-agent benchmark and detection system.
01
TL;DR
helm-ai-kernelSecurity & Safety · ★ 60
Governing and securing AI agent interactions with external systems and infrastructure.
ADRSecurity & Safety · ★ 2.1k
When to choose:
- You research detection for MCP-based agents and want to reproduce the MLSys 2026 ADR paper.
- You want a benchmark: ADR-Bench has 133 MCP servers and 303 tasks with baselines.
- You want to collect telemetry from Claude Code, Cursor and Codex into one schema with the sensor.
When to skip:
- You want a packaged product to deploy: this is research code for a paper.
- You want the ADR Explorer red-teaming engine: the README says it is not included.
- You cannot pay for Anthropic and OpenAI API calls: the default detector needs both.
02
Side-by-Side Comparison
Field
helm-ai-kernelADRCategory
Security & Safety
Security & Safety
Stars
★ 60
★ 2.1k
License
Apache-2.0
Apache-2.0
Install Command
brew install mindburnlabs/tap/helm-ai-kernel
git clone https://github.com/uber/ADR && cd ADR/Detection && uv sync
Updated
1d ago
4d ago
Open Source
Yes
Yes
Tags
AI Agent Security, Execution Firewall, Policy Enforcement
AI Agent Security, Telemetry, Detection System
03
Features
helm-ai-kernel01Enforces fail-closed, default-deny execution policies for AI agent tool calls.
02Provides a Multi-tool Call Protocol (MCP) wrapper to quarantine unknown tools before execution.
03Generates signed receipts and offline-verifiable EvidencePacks for audit and tamper-proofing of agent decisions.
04Offers an OpenAI-compatible proxy for integrating existing AI clients with policy enforcement.
05Supports multiple language SDKs (Go, Python, TypeScript, Rust, Java) for developer integration.
ADR01ADR Sensor for collecting and normalizing agent telemetry.
02ADR Detector, a dual-agent detection system with 133 MCP servers and 303 benchmark tasks.
03Support for the Model Context Protocol (MCP) for securing AI agents.
04Provides a step-by-step workflow to reproduce benchmark detection and paper figures.
04
Use Cases
helm-ai-kernel↳Governing and securing AI agent interactions with external systems and infrastructure.
↳Auditing and verifying the decisions (ALLOW, DENY, ESCALATE) made by AI agents for compliance.
↳Protecting against unauthorized or risky actions by AI agents through execution firewalls.
↳Integrating a security layer into existing OpenAI-compatible AI client workflows.
ADR↳Securing AI agents that use the Model Context Protocol (MCP).
↳Benchmarking and evaluating the security performance of agentic AI systems.
↳Collecting and analyzing telemetry data from various AI agent platforms.
↳Red-teaming and defensive security research for agentic AI.
05
Best For
helm-ai-kernel—
ADRTrending
FAQ
FAQ
What is the difference between helm-ai-kernel and ADR?
Both helm-ai-kernel and ADR are in the Security & Safety category. helm-ai-kernel has 60 stars, while ADR has 2.1k stars.
Which is better, helm-ai-kernel or ADR?
The best choice depends on your use case. Choose helm-ai-kernel if Governing and securing AI agent interactions with external systems and infrastructure., and ADR if Securing AI agents that use the Model Context Protocol (MCP)..
Is helm-ai-kernel free or open source?
Yes, helm-ai-kernel is open source on GitHub (Apache-2.0).
Is ADR free or open source?
Yes, ADR is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→