Agentic Sidecar attaches to your agent harness and evaluates every proposed tool call against policy, risk, intent, and budget limits before execution—without taking over the agent loop.
Test simulated agent actions against Policy Advisor, Risk Evaluator, Intent Guardian, and Budget Guardian in real time.
// Select an action to view the serialized Decision & DecisionContext payload.
Built on explicit governance boundaries rather than implicit LLM prompts.
Policy Advisor, Risk Evaluator, Intent Guardian, and Budget Guardian run deterministically with zero LLM latency or API costs. LLM Judges are strictly opt-in.
The Sidecar runtime (core/) has zero dependencies on specific framework adapters. It attaches to LangGraph, CrewAI, or custom loops seamlessly.
Requires an explicit on_sidecar_failure setting (fail_closed or fail_open). If evaluation errors, governance is guaranteed.
Enable only the evaluation components your application requires.
YAML-driven allow/deny permission rules matching tool names via glob patterns (delete_*).
Classifies actions into LOW, MEDIUM, or HIGH risk using tool argument pattern checks.
Validates tool parameters against structured user IntentEnvelope constraints and detects drift.
Enforces per-task spend (USD) and token ceilings, returning PAUSE for human approval when exceeded.
Evaluates entire agent plans to detect unnecessary steps, overreach, or contradictory operations.
Challenges decisions for unsupported assumptions and provides model-agnostic LLM decision review.
Gradually transition from monitoring to active policy enforcement.
| Mode | Behavior | Tool Execution | Use Case |
|---|---|---|---|
| Observe Mode | Evaluates tool calls, computes decision verdicts, and logs audit trails. | Always Executes | Initial deployment, shadow auditing, and baseline evaluation. |
| Govern Mode | ALLOW/WARN proceed. BLOCK stops; other outcomes resolve through approval or suspend execution. | Blocked via Exception | Production enforcement, financial boundary control, and safety gating. |
Simple, pythonic integration with LangGraph and agent frameworks.
# Wrap tools for LangGraph agent
from agentic_sidecar import Sidecar
from agentic_sidecar.adapters.langgraph import attach
from agentic_sidecar.gate.policy import PolicyAdvisor, PolicyRule
sidecar = Sidecar(
on_sidecar_failure="fail_closed",
mode="govern",
policy=PolicyAdvisor([PolicyRule(tool="delete_*", effect="deny")])
)
# Intercept tools before passing to react agent
tools = attach(sidecar, [read_order, issue_refund, delete_customer])
agent = create_react_agent(model, tools=tools)