Tool · curated 14 Jul 2026

GitHub - ClickHouse/code-interpreter: Sandboxed code execution API for AI agents: powers LibreChat's Code Interpreter

Coverage timeline

14 Jul 2026github.com

Single-source analysis — first reported, latest, and curated coincide.

Why it matters

Sandboxing tools like ClickHouse's code-interpreter give defenders a way to contain the risk of AI agents executing arbitrary or malicious model-generated code, a common attack surface in agentic systems.

ClickHouse's code-interpreter is an open-source sandboxed code execution API for AI agents, which powers LibreChat's Code Interpreter feature. The repository includes AppArmor profiles and CI hardening to isolate untrusted, agent-generated code execution.