agent-circuit

When tools fail, your agent degrades gracefully instead of looping.

Stop agent tool loops, enforce cost caps, and degrade gracefully. One decorator. Zero dependencies. Works with Claude Code, MCP, OpenAI Agents SDK, LangChain, and CrewAI.

Your agent calls a failing API. It retries 47 times. That burns $12, wastes 90 seconds, and your user stares at a spinner.

from agent_circuit import CircuitBreaker, CircuitDegraded

breaker = CircuitBreaker(max_failures=3, cost_global_limit=5.0)

@breaker.protect("search_api", cost_per_call=0.26)
def search(query: str) -> str:
    return api.search(query)

try:
    result = search("latest news")
except CircuitDegraded as e:
    print(e.result.message)     # "Search API unavailable"
    print(e.result.suggestion)  # "Skip and proceed with available info"

Result: 48 calls reduced to 4. $11.70 saved. 85 seconds saved.

pip install agent-circuit

python -m agent_circuit demo

No API keys needed. Shows before/after comparison with simulated failures.

One command setup. Protects all tool calls automatically:

agent-circuit install-hook

This adds PreToolUse and PostToolUse hooks to .claude/settings.local.json. Restart Claude Code to activate.

Check status:

agent-circuit status

Add circuit breaking to any MCP server:

from fastmcp import FastMCP
from agent_circuit.integrations.mcp import AgentCircuitMiddleware

mcp = FastMCP("my-server")
mcp.add_middleware(AgentCircuitMiddleware(max_failures=3))

@mcp.tool()
def search(query: str) -> str:
    return api.search(query)

Install: pip install agent-circuit[mcp]

from agents import Agent
from agent_circuit.integrations.openai_agents import protect_tools

agent = Agent(
    name="my-agent",
    tools=prot