In this section

🐍

Python SDK

Production-ready Python 3.11+. Hash-chain integrity, PII redaction, async batched transport, local disk buffer. MIT licensed.

TypeScript SDK

Identical receipt format, identical canonical-JSON hash. Wraps Claude Agent SDK and OpenAI Agents SDK. Public-beta Q3 2026.

🤖

OpenAI Agents SDK adapter

One-line wrap on the OpenAI Agents SDK runtime. Every tool call, model call, and sub-agent spawn captured as a receipt.

🧠

Claude Agent SDK adapter

Same primitive for Anthropic's Claude Agent SDK. Receipts capture model selection, tool routing, and sub-agent hierarchy.

🔌

MCP server adapter

Protocol-level capture. Wraps any MCP server so every tool call routed through it is automatically receipted, regardless of the agent host.

🦜

LangChain & CrewAI

Callback-based adapters for LangChain and CrewAI. Captures chain steps, agent decisions, and tool invocations at the framework boundary.

Five-minute quickstart.

# 1. Install the SDK
$ pip install agentaudit

# 2. Initialise in your agent code
import agentaudit
agentaudit.init(api_key="aa_live_...", agent_id="my_agent")

# 3. Wrap your framework — choose one:
agentaudit.instrument_openai_agents()
agentaudit.instrument_claude_agent()
agentaudit.instrument_mcp_server()

# 4. Your agent runs as normal — receipts flow automatically
agent.run(customer_query)

# 5. Verify chain integrity any time
$ agentaudit verify --agent my_agent --from 2026-06-01 --to 2026-06-07

Want help integrating?

During the open beta we pair-program the integration with your team. Half a day, then your receipts are flowing in production.

Start free → install in 5 minutes