AW-1 Circuit Breaker

Deterministic sub-0.2ms AST security circuit breaker for autonomous AI agents, tool dispatch pipelines, and MCP servers.

⚡ 10-Second Test Drive (Zero-Install)

Test the circuit breaker live in your terminal right now without installing anything:

uvx aw1-circuit-breaker --demo

Or verify an arbitrary snippet:

uvx aw1-circuit-breaker verify "subprocess.run(['rm', '-rf', '/'])"

AW-1 Circuit Breaker

Deterministic AST deconstruction and runtime circuit breaker preventing rogue shell escapes, dynamic eval(), and covert lateral socket egress in autonomous LLM tool calls.

Installation

pip install -r requirements.txt

Running the Server

Run directly with Python:

python mcp_server.py

Or via uvx:

uvx mcp_server.py

MCP Client Configuration

{
  "mcpServers": {
    "aw1-circuit-breaker": {
      "command": "python",
      "args": ["mcp_server.py"]
    }
  }
}

Exploit Interception in Action

AW-1 operates deterministically at the Abstract Syntax Tree (AST) level before code reaches Python's runtime execution frame. Probabilistic prompt-based guardrails fail under encoding obfuscation; AST inspection guarantees deterministic enforcement.

Interception Matrix

Run the Showcase

python examples/exploit_showcase.py

Runtime Latency Telemetry

Deterministic security must not throttle agent execution. AW-1 operates with sub-millisecond AST parsing and microsecond-scale argument filtering across warm execution loops.

Sample Size: 1,000 synthetic iterations per test vector on Debian Python 3.13.

Reproduce locally:

python benchmark.py

Framework Integration (LangGraph Example)

AW-1 drops directly into autonomous agent execution nodes prior to tool dispatch:

from examples.langgraph_adapter import execute_agent_action, CircuitBreakerException

# Guard autonomous agent tool dispatches
try:
    execute_agent_action(bash_tool, "bash_tool", {"cmd": "cat log.txt; rm -rf /"})
except CircuitBreakerException as blocked:
    print(f"Tool call halted: {blocked}")

License

Licensed under the Apache License, Version 2.0. See LICENSE for details.