§ INTEGRATIONS
Governance for every agent framework
Plug Execlave into your existing agent stack with a callback handler, tracing processor, or one-line helper. Policies enforce before the LLM call; traces stream to your dashboard.
First-party framework support
Every integration below is covered by automated tests and ships under the SDK you already have installed.
LangChain
Drop-in callback handler that instruments chains, LLMs, tools, agents, and retrievers. Enforcement runs on every chain entry and every tool call.
OpenAI Agents SDK
Tracing processor that hooks into the Agents SDK to capture agent/tool/generation spans and block disallowed tools before they run.
CrewAI
One call to instrument_crew() wires in step and task callbacks, chaining your existing callbacks rather than replacing them.
AutoGen
instrument_autogen_agent() wraps generate_reply so every conversation round runs through enforcement and every tool_calls / function_call entry is gated by tool-allowlist policies.
LlamaIndex
Dispatcher event handler for queries, LLM calls, retrievals, and agent tool calls. Enforces policies before tool execution and on the top-level query.
n8n
No-code workflow integration via HTTP Request nodes — templates for enforcement, approval polling, and trace ingestion.
OpenAI (Chat Completions)
instrument_openai() wraps the openai SDK client so every chat.completions.create enforces policies on the user prompt and records an LLM span with model + token usage.
Model Context Protocol
Wrap an MCP ClientSession / Client so every callTool runs through tool-allowlist enforcement before the request reaches the MCP server.