ephemora-cell
★ 48
vs
ADR
★ 2.1k
ephemora-cell vs ADR
ephemora-cell: Ephemora Cell is an execution layer designed for running untrusted AI-generated code safely within a capability-based WASM environment. It provides strict resource limits and enforces security boundaries to protect the host system from potentially malicious or buggy code.; 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
ephemora-cellSecurity & Safety · ★ 48
Securely executing AI-generated code with predefined resource and access limits.
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
Category
Security & Safety
Security & Safety
Stars
★ 48
★ 2.1k
License
Apache-2.0
Apache-2.0
Install Command
pip install ephemora-cell
git clone https://github.com/uber/ADR && cd ADR/Detection && uv sync
Updated
1d ago
4d ago
Open Source
Yes
Yes
Tags
WASM Runtime, Code Sandboxing, AI Agent Security
AI Agent Security, Telemetry, Detection System
03
Features
01Enforced, fine-grained resource limits (CPU, memory, time, I/O, filesystem).
02Robust security, blocking 8/8 common attack vectors against host systems.
03Sub-millisecond warm execution for scalable and affordable sandboxing.
04Generates sign-ready, auditable execution records (JCS canonicalization + ES256).
01ADR 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
↳Securely executing AI-generated code with predefined resource and access limits.
↳Building robust plugin systems for user-uploaded code without compromising host security.
↳Operating as a Multi-Modal Command Protocol (MCP) server for AI agents, providing isolated tool execution.
↳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
—
Trending
FAQ
FAQ
What is the difference between ephemora-cell and ADR?
Both ephemora-cell and ADR are in the Security & Safety category. ephemora-cell has 48 stars, while ADR has 2.1k stars.
Which is better, ephemora-cell or ADR?
The best choice depends on your use case. Choose ephemora-cell if Securely executing AI-generated code with predefined resource and access limits., and ADR if Securing AI agents that use the Model Context Protocol (MCP)..
Is ephemora-cell free or open source?
Yes, ephemora-cell 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.
→