Glossary
Human approval
Human approval is defined here as follows. A pause where a person inspects or changes agent state before the run continues. LangGraph provides this inside the graph. The directory source for this term is LangGraph overview. Last verified 2026-10-17. The directory lists 4 entries that use this term.
Last verified 2026-10-17
Sources
Listings
Directory listings whose sources describe this mechanism.
| Name | Status | Category | Open source | Mechanism |
|---|---|---|---|---|
| LangGraph | Live | Frameworks and runtimes | Yes | Low level orchestration runtime for long running stateful agents, with durable execution and human checkpoints inside the graph. orchestration, approvals, state |
| Mastra | Live | Frameworks and runtimes | Yes | Open source TypeScript framework for agents and workflows, with memory, tool approvals, and processors that can block or redact content. typescript, orchestration, approvals |
| Microsoft Agent Framework | Live | Frameworks and runtimes | Yes | Open framework for building and orchestrating agents and multi agent workflows in Python and .NET, with graph workflows and human checkpoints. multi-agent, orchestration, approvals |
| OpenAI Agents SDK | Live | Frameworks and runtimes | Yes | Library that runs an agent loop in your application, with tools, handoffs, guardrails, sessions, and human approval before a tool runs. orchestration, tools, approvals |
Questions
- What is Human approval?
- A pause where a person inspects or changes agent state before the run continues. LangGraph provides this inside the graph.
- Which listings use Human approval?
- LangGraph, Mastra, Microsoft Agent Framework, OpenAI Agents SDK.
- When was Human approval last verified?
- Last verified 2026-10-17.