# Stop before a risky tool call until a person approves (slim)

> Stop before a risky tool call until a person approves: 2 companies fully do it, 14 with a limit, 35 carry the tag. Every listing in Agent frameworks & SDKs with the reason and a source.

- Full: https://www.anchorterminal.com/niches/frameworks.human-approval/index.md (~2,050 tokens) · this version ~380 tokens · JSON https://www.anchorterminal.com/niches/frameworks.human-approval/index.json · canonical https://www.anchorterminal.com/niches/frameworks.human-approval/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-15
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Two or three companies' docs show a full fit. Full fit: 2 companies, with a limit: 14, tagged: 35. Weight 10, 7 accounts.

Done when: Tools marked as needing approval do not run until approved, in code rather than prompt, the pending call with its arguments is readable by the host, approve, edit or reject resumes the same run through an API after a process restart, and the wait has no built-in timeout shorter than a day or one that can be set.
yes: claude-agent-sdk (Anthropic, PBC)
yes: pydantic-ai (Pydantic Services Inc.)
caveat: agentos (Framers Lab, Inc.)
caveat: agno (Agno Inc.)
caveat: boxlang-ai (Ortus Solutions, Corp.)
caveat: crewai (CrewAI, Inc.)
caveat: cursor-agent-sdk (Anysphere, Inc.)
caveat: docker-agent (Docker, Inc.)
caveat: google-adk (Google LLC)
caveat: langgraph (LangChain, Inc.)
caveat: llamaindex (LlamaIndex, Inc.)
caveat: mastra (Kepler Software, Inc.)
caveat: microsoft-agent-framework (Microsoft Corporation)
caveat: openai-agents-sdk (OpenAI OpCo, LLC)
caveat: strands-agents (Amazon Web Services, Inc.)
caveat: vercel-ai-sdk (Vercel Inc.)

Data: https://www.anchorterminal.com/api/v1/use-cases/frameworks.human-approval.json
