Agent Code Executor

Visualize AI writing and executing code in a sandboxed environment with real-time output, execution history, and security controls.

Features

Code Display: Syntax-highlighted editor view showing the agent's generated code
Output Panel: Live stdout, stderr, and return-value output from the sandboxed execution
Execution History: Browse previous runs with input snapshots and result diffs
Security Indicators: Visual badges showing sandbox isolation level and permission scope
Sandbox Controls: Start, stop, and restart execution with resource usage limits

Examples

Data Processing Script

Code execution

renewal-analysis · Python · sandboxed

Code

import pandas as pd

renewals = pd.read_csv("renewals_q3.csv")
at_risk = renewals.query("risk_score >= 0.7")
print(at_risk.groupby("owner")["renewal_value"].sum())

OutputExit 0

Morgan Lee     520000
Jordan Kim     410000
Priya Shah     360000

Previous runs2

01at_risk = renewals.query("risk_score >= 0.7")Succeeded2 min ago
Code
```
at_risk = renewals.query("risk_score >= 0.7")
print(len(at_risk))
```
Output
```
12
```
Run run-2Exit 00.38s24.1 MB

02renewals = pd.read_csv("renewals_q3.csv")Failed5 min ago

Code

renewals = pd.read_csv("renewals_q3.csv")
print(renewals.columns)

Output

FileNotFoundError: renewals_q3.csv

Run run-1Exit 10.09s21.8 MB

Installation