Sandboxes and execution environments for running agent code/tools. Ranked by community traction, with live GitHub stars and what each is best at.
Short answer: the best agent runtimes for AI agents by community traction is Temporal (★ 22k), followed by E2B.
✓ Live data verified
Durable execution platform — write long-running, failure-resilient agent workflows as ordinary code. Best for durable agent workflows.
Secure cloud sandboxes for running AI-generated code — the runtime layer for code-executing agents. Best for code execution.
By community traction, Temporal (★ 22k) leads the agent runtimes in our directory. Durable execution platform — write long-running, failure-resilient agent workflows as ordinary code.
Temporal is the most-starred open-source option; E2B and others are strong runners-up.
Temporal, at ★ 22k (live count).
We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.