# Claude Agent SDK (slim)

> Runs the Claude Code agent as a library, with its loop, built-in tools, permissions, sessions, hooks and subagents.

- Full: https://www.anchorterminal.com/tools/claude-agent-sdk.md (~5,150 tokens) · this version ~1,330 tokens · JSON https://www.anchorterminal.com/tools/claude-agent-sdk.json · canonical https://www.anchorterminal.com/tools/claude-agent-sdk
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**BB · 72.4/100 · rank #71 of 452 · #4 in Agent frameworks & SDKs · agent-ready · confidence medium**


Assessment: Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks. Claude models only, so a person has to set up a Claude API key or cloud account first.

Disclosure: Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.

## Facts

- Kind: Agent framework · vendor: Anthropic · category: Agent frameworks & SDKs · legal entity: Anthropic, PBC · provenance 100/100
- Packages: pypi `claude-agent-sdk`, npm `@anthropic-ai/claude-agent-sdk`
- Auth: API key · pricing: Free · x402: no · licence: MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary)
- Languages: Python, TypeScript
- Models: Claude only, through the Claude API, Bedrock, Google Cloud or Foundry
- MCP client: stdio, SSE, streamable HTTP, in-process
- Multi-agent: Subagents
- Durable state: Local sessions with resume and fork
- Human approval: Permission modes, approval callback, hooks
- Tracing: OpenTelemetry, opt-in
- Telemetry: On by default via the bundled CLI. `DISABLE_TELEMETRY=1`
- Releases in 90 days: About 50
- Hosted runtime: Managed Agents (beta), $0.08 a session-hour plus tokens
- Prices: Managed Agents runtime (beta) $0.08 per session-hour
- 2026-08-04 Breaking change: 0.2.129 raises `ValueError` on invalid skill names

- Scores: Reliability 70, Performance pending, Schema & documentation 89, Agent ergonomics 94, Security & auth 83, Payments & pricing 40, Task success pending, Maintenance & community 87, Transparency & trust 86 · negative events -6 · total over the 7 assessed categories
- Why: Reliability, Official packages on PyPI (Requires-Python >=3.10) and npm (node >=18) (20). · Schema & documentation, Typed public interfaces with a full Python and TypeScript reference, options as dataclasses and TypedDicts (25). · Agent ergonomics, The documented agent with one MCP server is about 15 lines with the built-in client, and tool search withholds MCP tool definitions by defau… · Security & auth, Usage metrics go to Anthropic and third-party logging by default on the Claude API, without code, prompts or file paths, and DISABLE_TELEMET… · Payments & pricing, No payment protocol (0). · Maintenance & community, Python 0.2.163 on 2026-09-30 (30). · Transparency & trust, The Python wrapper is MIT, but its wheel bundles the proprietary Claude Code binary, and the TypeScript package says All rights reserved und…
- Sources: 14, open questions: 5, both in the full twin
- Capabilities: agent.framework, agent.multi-agent, agent.mcp-client
- JSON: https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/claude-agent-sdk.svg` or a link to https://www.anchorterminal.com/tools/claude-agent-sdk from a page on claude.com or anthropic.com or one of their subdomains, or the README of github.com/anthropics/claude-agent-sdk-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set DISABLE_TELEMETRY=1 before the first run on the Claude API
2. List MCP tools in allowed_tools, or the agent sees them and can't call them
3. Pass permission_mode explicitly. An unset mode can start in auto mode since TypeScript 0.3.286
4. Pin the version. Releases land almost daily and some get yanked
5. Check the init message for MCP servers in failed or needs-auth. They don't raise

## Connect

```bash
pip install claude-agent-sdk   # or: npm i @anthropic-ai/claude-agent-sdk
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI Agents SDK | AA | 86.5 | agent.framework, agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/openai-agents-sdk.min.md |
| Pydantic AI | A | 80 | agent.framework, agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/pydantic-ai.min.md |
| Agent Development Kit (ADK) | BB | 74.9 | agent.framework, agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/google-adk.min.md |
| LangGraph | BB | 70.6 | agent.framework, agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/langgraph.min.md |
| CrewAI | B | 67 | agent.framework, agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/crewai.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)