ephemora-cell
Active·★ 48·Apache-2.0·Updated 2026-10-22
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.
#WASM Runtime#Code Sandboxing#AI Agent Security#Untrusted Code Execution#Resource Management#Execution Layer#Security Auditing
01
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).
02
Compatibility
Python
Runtime
Verified via docs
WASM
Execution Environment
Verified via docs
macOS
OS
Verified via docs
Linux
OS
Verified via docs
03
Quick start
1
$ pip install ephemora-cell
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.
05
Alternatives
ADR★ 2.1k
ADR (Agentic Detection and Response): open-source telemetry sensor and dual-agent detection framework for securing MCP-based AI agents.
AgentHound★ 452
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
helm-ai-kernel★ 60
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
pic-standard★ 68
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
agentshield★ 21
🛡️ The security firewall for AI agent tools & MCP servers (Claude, GPT-5.6, Gemini 3.7, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.
phantom-secrets★ 18
Stop AI coding agents from leaking your API keys. Local proxy + MCP that swaps real secrets for phm_ tokens — works with Claude Code, Cursor, Windsurf, and Codex.
Comments
Log in to leave a comment
No comments yet. Be the first!