CodeShield: Autonomous Code Execution Engine

Deterministic, Isolated, and Self-Healing Python Execution Runtime for AI Agents.

This open-source engine executes Python code generated by LLMs inside a disposable, isolated sandbox, validates it statically with the Python ast module, and recovers from runtime errors through a deterministic self-healing loop backed by local heuristics and plug-and-play LLM-guided patch generation (OpenAI, Anthropic Claude, DeepSeek, Ollama, Google Gemini).

Comparison

Feature	Vanilla subprocess	Docker Container	CodeShield (This Engine)
Startup Overhead	~5 – 10 ms	~1,500 – 3,000 ms	Sub-second (~30–250 ms via uv)
Isolation Mechanism	None (Host Process)	Container Namespaces / cgroups	Ephemeral Virtualenv (tempfile + uv)
AST Security Gate	❌ None	❌ None	✅ Static AST inspection (os.system, eval)
Silent Failure Detection	❌ None	❌ None	✅ Regex scanning for empty DataFrames/NaNs
Self-Healing Loop	❌ None	❌ None	✅ 3-Tier Traceback Diagnosis + LLM Patch (Any Provider)

---

Architecture

[LLM Generated Code]
        │
        ▼
[AST Static Gate] ──(Syntax/Security Violation)──► [Validation Error Report]
        │ (Passed)
        ▼
[uv Isolated Sandbox] ──(Runtime Error/Silent Failure)──► [Traceback Classifier]
        │                                                          │
        │ (Clean Execution: exit 0)                                ▼
        ▼                                               [LLM Self-Healing (Any Provider) / Local Heuristic]
[Verified Output (JSON)] ◄──(AST Validated Patch)─────────────────┘

---

Key Features

1. Ephemeral Sandboxing with Dual-Mode Backend

• Primary: uv venv for ultra-fast environment creation and package installation.
• Fallback: native python -m venv + pip when uv is unavailable, so the engine works out of the box on any machine.
• Each execution lands in its own temporary workspace that is destroyed after use.

2. Deterministic AST Security Gates

The engine parses every snippet with the standard ast module and rejects:

• SyntaxErrors before execution.
• Bare except: / except Exception: / except BaseException: handlers.
• Calls to dangerous parametrizable functions: eval(), exec(), compile().
• Calls to system/subprocess primitives: os.system(), subprocess.call(), subprocess.run(), subprocess.Popen().

3. Silent Failure Detection

Even when a process exits with 0, the engine flags suspicious output patterns such as:

• empty DataFrame
• all NaN
• Traceback
• Pipeline failed
• Fatal Error

4. Model-Agnostic Self-Healing Loop

AST Validation ──► Sandbox Execution ──► Traceback Classification ──► Patch ──► Re-run
                                      (3 attempts max)

• Local heuristic fallback: handles NameError, ImportError, ModuleNotFoundError by injecting safe imports or placeholder definitions.
• LLM-guided healing: when an LLM is configured (built-in Gemini Flash by default, or any custom provider via patch_generator), it asks the model for a corrected version of the code, validates it with the AST gate, and re-executes the patched snippet.

---

Quickstart

Installation

# Install from PyPI
pip install codeshield-runtime

# Install with all extras (LLM + Dev tools)
pip install "codeshield-runtime[llm,dev]"

# Or clone for development
git clone https://github.com/AlgorithmicMind/codeshield.git
cd codeshield

# With uv (recommended)
uv venv
uv pip install -e ".[test,lint,llm,dev]"

# Or with pip
python -m venv .venv
.venv\Scripts\activate  # Windows
pip install -e ".[test,lint,llm,dev]"

Offline Usage (No API Key)

from codeshield.loop import SelfHealingEngine

engine = SelfHealingEngine(use_llm=False)
with engine:
    result, diagnosis = engine.run("print('hello world')")
    print(result.stdout)

Model-Agnostic Self-Healing (Plug-and-Play)

CodeShield is not locked into a single LLM. Pass any Python callable as the patch_generator to use OpenAI, Anthropic Claude, DeepSeek, Ollama, LiteLLM or your own service:

from codeshield.loop import SelfHealingEngine


def custom_llm_patcher(code: str, diagnosis) -> str:
    # Compatible with any frontier provider: GPT-5.4, Claude Sonnet 5, DeepSeek V4, Ollama
    response = client.chat.completions.create(
        model="gpt-5.4-mini",  # or "claude-sonnet-5", "deepseek-v4-flash"
        messages=[
            {
                "role": "user",
                "content": f"Fix this code:\n{code}\nError: {diagnosis.message}",
            }
        ],
    )
    return response.choices[0].message.content


engine = SelfHealingEngine(patch_generator=custom_llm_patcher)

Zero-Config Self-Healing with Gemini Flash

For the built-in zero-config experience, create a .env file from .env.example:

GEMINI_API_KEY=your_key_here
GEMINI_MODEL=gemini-3.7-flash

from dotenv import load_dotenv
from codeshield.loop import SelfHealingEngine

load_dotenv()

engine = SelfHealingEngine()
with engine:
    result, diagnosis = engine.run('print("Result: " + 42)')
    print(result.stdout)  # Result: 42

Run the included demo:

python demo.py

CLI Usage

Execute any Python file directly from the terminal with the built-in CLI:

python -m codeshield run script.py
python -m codeshield run script.py --timeout 30
python -m codeshield run script.py --llm        # try LLM self-healing if configured
python -m codeshield run script.py --no-llm     # force local fallback

🤖 Agent Tool Integration (LangChain, CrewAI, OpenAI, Gen AI)

from codeshield import create_code_execution_tool

# Pass the tool directly to your agent
tools = [create_code_execution_tool()]

create_code_execution_tool() returns a ready-to-register execute_python_code(code: str) -> str function. It runs the provided Python in a self-healing sandbox and returns either the stdout or a structured error report with error_type and stderr.

---

Verified Examples

The examples/ folder contains ready-to-run recipes that have been executed and verified:

• 01_basic_sandboxing.py: isolated execution with timing measurements.
• 02_security_gatekeeper.py: AST rejection of unsafe code.
• 03_llm_healing_workflow.py: self-healing workflow with an LLM or local fallback.
• 04_agent_tool_dropin.py: end-to-end agentic tool-calling workflow with dynamic code generation.
• 05_custom_llm_openai_compatible.py: model-agnostic, API-key-free self-healing with a custom patch_generator.

python examples/01_basic_sandboxing.py
python examples/02_security_gatekeeper.py
python examples/03_llm_healing_workflow.py
python examples/04_agent_tool_dropin.py
python examples/05_custom_llm_openai_compatible.py

Running Tests & Lint

The suite currently has 53 tests with >82% code coverage on src/codeshield.

ruff check src tests examples
pytest tests -v --cov=src/codeshield

---

Enterprise Architecture & Custom Deployments

This repository ships the core execution and healing engine. For production multi-tenant deployments, the enterprise extension adds:

• Multi-tenant orchestrator with queue-based job scheduling.
• PostgreSQL state persistence for execution history, audit trails and replay.
• Automated billing and token governance (cost caps per tenant, per-execution budgets).
• Prometheus/Grafana observability, RBAC, and signed artifact provenance.
• SLA-backed support and custom agentic architecture consulting.

Want the production-grade version or a tailored integration for your platform?

• Open a GitHub issue
• Connect on LinkedIn

We offer enterprise licensing, dedicated onboarding and custom agentic-architecture consulting.

---

License

This project is licensed under the MIT License. See LICENSE for details.