Integration Guides
RADAR does not require SDK installation, agent rewrites, or framework-specific adapters. It connects beside your existing infrastructure by consuming telemetry from your LLM gateway, tool execution logs, or model response streams.
How integration works
- Name
Gateway tap- Description
Connect to your LLM gateway via log ingestion or event stream. RADAR captures prompts, completions, and metadata without modifying gateway configuration.
- Name
Sidecar proxy- Description
Deploy RADAR as a sidecar that observes agent-to-LLM traffic. No agent code changes. Supports OpenTelemetry and custom webhook formats.
- Name
API push- Description
Send evidence events directly from your agent runtime via REST API. Explicit control over what gets recorded and when.
LangChain
Integrate via LangChain callback system or gateway log ingestion. Gateway log ingestion is recommended — zero agent code changes. Supported gateways: OpenAI, Azure OpenAI, Anthropic, any gateway exposing OpenTelemetry traces or structured JSON logs.
LangGraph
RADAR observes full graph execution — node transitions, tool calls between nodes, and final outputs — through gateway telemetry. Every node execution is recorded as a trace event. Tool calls within graph nodes are captured independently and mapped back to the parent node.
CrewAI
Each agent in the crew produces independent traces. RADAR correlates them under a single crew session ID for end-to-end audit. When agents hand off tasks, RADAR captures the handoff context and authorization boundary crossed.
Custom stacks
For proprietary stacks, use the REST API to push structured evidence events. Also supports webhook receivers, log file ingestion, and OpenTelemetry traces from any agent runtime. Compatible with any language and framework.