getlark/runtimeuse

Run AI agents inside sandboxes over WebSockets

34
/ 100
Emerging

Provides a TypeScript runtime that executes inside sandboxes and a Python client library for remote interaction, enabling AI agents to fetch external resources, execute code, and return structured results over WebSocket. Supports pluggable LLM handlers (OpenAI, Claude) and pre-execution environment setup through downloadable artifacts, allowing agents to operate on fetched codebases or datasets without leaving the sandbox boundary.

Available on npm.

Maintenance 13 / 25
Adoption 3 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

4

Forks

—

Language

TypeScript

License

—

Category

agent-code-sandboxing

Last pushed

Mar 18, 2026

Commits (30d)

0

Dependencies

5

GitHub npm
Agent Code Sandboxing · 113 agents

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/getlark/runtimeuse"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Featured in

Agent Governance in 2026: Who's Building the Guardrails? Agent Platforms Are Four Problems, Not One

Higher-rated alternatives

e2b-dev/E2B

Open-source, secure environment with real-world tools for enterprise-grade agents.

92

alibaba/OpenSandbox

OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language...

87

e2b-dev/infra

Infrastructure that's powering E2B Cloud.

76

boxlite-ai/boxlite

Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.

64

always-further/nono

Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with...

63

Explore AI Agents

All categories Trending AI Agent directory Insights