Claude Agent SDK
BetaAnthropic's native agent SDK.
TypeScript and Python SDKs published by Anthropic for building agents on top of Claude with native tool use, computer use, and multi-step workflows. Used internally by NanoClaw as its underlying runtime.
- Category
- Developer frameworks
- Runtime
- Node.js / TypeScript
- Pattern
- SDK / Library
- Adapter package
- @intramedial/actor-claude-sdk
Status
Claude Agent SDK is Beta.
The integration path is built and tested. Customers can attach now; expect minor breaking changes until the 1.0 contract freeze.
Ships from the repo as `@intramedial/actor-claude-sdk` — not yet on a package registry.
How to attach
SDK / Library.
Install the adapter
Add @intramedial/actor-claude-sdk to your project.
Issue a workspace API key
Generate a key in the dashboard under Settings → API Keys, scoped to the workspace and environment this agent's data should land in.
Record each run
Construct the adapter once with your token and workspace id where you initialise your Claude Agent SDK agent, then call recordRun(run) when a run finishes. The adapter maps the run to signed receipts and, by default, captures a failed attestation instead of crashing your agent.
Verify
Trigger one agent run. The Witness page shows the record once the agent has emitted it.
What gets recorded
2 event types, captured today.
- agent.invocation
- Every top-level agent run — the input, the resolved output, timing and token usage.
- tool.call
- Each tool or function the agent invokes, with its arguments and returned result.
Same category
Others in Developer frameworks.
The reference library for building agent applications.
- CrewAIBeta
Multi-agent crew orchestration.
- AutoGen / AG2Beta
Microsoft's multi-agent conversation framework.
OpenAI's native agent framework.
- Vercel AI SDKBeta
TypeScript-first toolkit for agentic applications.
- MastraBeta
TypeScript framework for production agents.
Start recording Claude Agent SDK agents.
Every Claude Agent SDK run lands in the same canonical Witness record as every other framework in the catalogue: signed, replayable, and exportable as evidence.
A Trustvice ProductAgents act when the plane says yes, and the record says why.
Put admission in front of your MCP servers, repositories, SaaS tools and cloud accounts. Every agent gets a lease or a reason – and you keep the lever to stop any of them.
