python-executor
Execute Python code in isolated E2B sandboxes with SONA learning
$ npx -y skills add ruvnet/agentic-flow --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Execute Python code in isolated E2B sandboxes with SONA learning
Agent definition
python-executor.mdname: python-executor
version: 1.0.0
capability: python-executor
description: Execute Python code in isolated E2B sandboxes with SONA learning
features:
- e2b-sandbox
- sona-learning
- quic-sync
- trajectory-tracking
Python Executor Agent
Executes Python code in isolated E2B Firecracker sandboxes with SONA Micro-LoRA learning.
Capabilities
- **E2B Sandbox**: Isolated code execution via E2B Code Interpreter
- **SONA Learning**: Micro-LoRA adaptation (~0.05ms) for improved routing
- **QUIC Sync**: Fast state synchronization across agents
- **Trajectory Tracking**: Reinforcement learning from execution outcomes
Usage
import { E2BSwarmOrchestrator } from 'agentic-flow/sdk';
const swarm = new E2BSwarmOrchestrator();
await swarm.spawnAgent({
id: 'python-1',
name: 'Python Executor',
capability: 'python-executor',
packages: ['numpy', 'pandas', 'matplotlib']
});
const result = await swarm.executeTask({
id: 'task-1',
type: 'python',
code: 'import numpy as np; print(np.mean([1,2,3,4,5]))'
});Learning Integration
import { learnFromEpisode, getAlgorithmForTask } from 'agentic-flow/hooks';
// Get recommended algorithm
const { algorithm } = getAlgorithmForTask('agent-routing');
// => 'double-q' for reduced overestimation bias
// Learn from execution outcome
await learnFromEpisode('agent-routing', 'python-task', 'python-executor', result.success ? 1.0 : 0.0, 'next-state', true);Environment Variables
- `E2B_API_KEY` - E2B API key for sandbox creation
- `AGENTIC_FLOW_LEARNING_RATE` - SONA learning rate (default: 0.1)
- `AGENTIC_FLOW_MEMORY_BACKEND` - Memory backend (agentdb/sqlite)
Read more
name: python-executor version: 1.0.0 capability: python-executor description: Execute Python code in isolated E2B sandboxes with SONA learning features: - e2b-sandbox - sona-learning - quic-sync - trajectory-tracking
Python Executor Agent
Executes Python code in isolated E2B Firecracker sandboxes with SONA Micro-LoRA learning.
Capabilities
- **E2B Sandbox**: Isolated code execution via E2B Code Interpreter
- **SONA Learning**: Micro-LoRA adaptation (~0.05ms) for improved routing
- **QUIC Sync**: Fast state synchronization across agents
- **Trajectory Tracking**: Reinforcement learning from execution outcomes
Usage
import { E2BSwarmOrchestrator } from 'agentic-flow/sdk';
const swarm = new E2BSwarmOrchestrator();
await swarm.spawnAgent({
id: 'python-1',
name: 'Python Executor',
capability: 'python-executor',
packages: ['numpy', 'pandas', 'matplotlib']
});
const result = await swarm.executeTask({
id: 'task-1',
type: 'python',
code: 'import numpy as np; print(np.mean([1,2,3,4,5]))'
});Learning Integration
import { learnFromEpisode, getAlgorithmForTask } from 'agentic-flow/hooks';
// Get recommended algorithm
const { algorithm } = getAlgorithmForTask('agent-routing');
// => 'double-q' for reduced overestimation bias
// Learn from execution outcome
await learnFromEpisode('agent-routing', 'python-task', 'python-executor', result.success ? 1.0 : 0.0, 'next-state', true);Environment Variables
- `E2B_API_KEY` - E2B API key for sandbox creation
- `AGENTIC_FLOW_LEARNING_RATE` - SONA learning rate (default: 0.1)
- `AGENTIC_FLOW_MEMORY_BACKEND` - Memory backend (agentdb/sqlite)
Production-ready AI agent orchestration with 66 self-learning agents, 213 MCP tools, and autonomous multi-agent swarms.
Repo: ruvnet/agentic-flow
Other agents on agentic-flow.
- analyze-code-quality
Advanced code quality analysis agent for comprehensive code reviews and improvements
Open agent - code-analyzer
Advanced code quality analysis agent for comprehensive code reviews and improvements
Open agent - arch-system-design
Expert agent for system architecture design, patterns, and high-level technical decisions
Open agent - base-template-generator
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized.
Open agent - README
Specialized agents for distributed consensus mechanisms and fault-tolerant coordination protocols
Open agent - byzantine-coordinator
Coordinates Byzantine fault-tolerant consensus protocols with malicious actor detection
Open agent

