Privacy choices: we'd like to measure visits anonymously (our own cookie-free counter plus Google Analytics, which sets its own cookies; no ads) and load Beehiiv's newsletter sign-up, which may set its own cookies. Nothing optional runs until you choose. Privacy policy

AgentScout / Tasks / Evaluating agents / Sandboxes and secure execution

Sandboxes and secure execution tools for agent evaluation

Isolated sandboxes where agents can run code and tools away from your machine and data. Of the 426 tools on our evaluating agents page, 9 fit this narrower job. By pricing: 6 open source, 2 free or freemium, 1 pricing on the maker's site. The most-starred open repos here are Cua (31,341 stars), LangChain Deep Agents (30,785 stars), rLLM (5,925 stars). Most come from the frameworks (3), evals & observability (3), browser/computer use (1) categories.

Updated

Cua logo

Cua

browser/computer useOpen source + cloud

Open-source infrastructure for computer-use agents: sandboxes, drivers across operating systems and benchmarks.

Added

LangChain Deep Agents logo

LangChain Deep Agents

frameworksOpen source

Deep Agents is LangChain's MIT-licensed, batteries-included agent harness for long-horizon, multi-step work: an opinionated agent that runs out of the box and lets you override or replace any piece. It provides sub-agents with isolated context windows, a pluggable filesystem (local, sandboxed or remote), context summarisation and offloading, shell access in your sandbox, persistent memory and human-in-the-loop approvals. It is model-agnostic for any tool-calling LLM and builds on LangGraph, with tracing, evals and deployment through LangSmith.

Added

rLLM logo

rLLM

frameworksOpen source

rLLM is an Apache-2.0 framework for training language agents with reinforcement learning. You bring any harness, including 10+ CLI agents such as Claude Code, Codex, mini-swe-agent and OpenCode, or wrap your own LangGraph or OpenAI Agents SDK agent with @rllm.rollout, run it in Docker, Daytona, Modal or local sandboxes, and switch training backends with one flag. The same agent code drives both evaluation and training.

Added

ToolHive logo

ToolHive

MCP serversOpen sourceNot yet checked

Stacklok platform that runs MCP servers in isolated containers with per-request identity, access policy and observability.

Added

Sage logo

Sage

frameworksOpen source

Sage is an open-source (MIT) RSI agent harness, where RSI stands for Recursive Self-Improvement: it improves agents using feedback from their tasks. Starting from a goal or a curated usage history, it runs the agent, has a separate evaluator grade the results, tunes the agent and keeps every version with its evidence, so you decide which one to adopt. It comes as a Desktop app, a multi-user Server with Agent Studio, and the SAgents Python runtime, with support for Skills, MCP, multi-agent setups and sandboxed runs with approvals.

Added

AgentEnv Framework logo

AgentEnv Framework

evals & observabilityOpen source

AgentEnv Framework is Scale AI's open-source Python SDK and CLI for building RL environments for agents: containerized worlds with realistic apps and data behind an MCP gateway, plus tasks (as DAGs) that grade any agent in any sandbox.

Added

Runtm logo

Runtm

evals & observabilitySee site

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Added

CoreWeave Forge logo

CoreWeave Forge

evals & observabilityFreemium

One product to run, observe, evaluate and post-train agents (W&B, OpenPipe, sandboxes).

Added

Solari logo

Solari

Newsandboxes & code executionFreemium

Solari gives AI agents three kinds of cloud environment from one API: headless cloud browsers that start in about 8 ms for browsing, logging in and scraping, isolated sandboxes that start in about 90 ms for running code and tools, and full computer desktops an agent can drive like a person. Sessions are billed per second while they run, with replay recordings and stealth mode on paid plans. Solari publishes its own latency benchmark against Browserbase, Steel, Kernel and Hyperbrowser. A free plan covers prototyping; Starter is $20 a month and Professional $200.

Added

GitHub repos (7)

RepoGitHub starsLicenceLast push
Cua logoCua ↗31,341MIT2026-10-30
LangChain Deep Agents logoLangChain Deep Agents ↗30,785MIT2026-10-30
rLLM logorLLM ↗5,925——
ToolHive logoToolHive ↗2,316Apache 2.02026-10-30
Sage logoSage ↗1,216—2026-10-30
AgentEnv Framework logoAgentEnv Framework ↗394—2026-10-30
Runtm logoRuntm ↗304——

7 repos. Stars and licence come from each repo, checked when the listing was last verified.

FAQ

What are the best AI tools for evaluating agents focused on sandboxes and secure execution?

We list 9. The first three by GitHub stars and featured status are Cua: Open-source infrastructure for computer-use agents: sandboxes, drivers across operating systems and benchmarks.; LangChain Deep Agents: Deep Agents is LangChain's MIT-licensed, batteries-included agent harness for long-horizon, multi-step work: an opinionated agent that runs out of the box and lets you override or replace any piece. It provides sub-agents with isolated context windows, a pluggable filesystem (local, sandboxed or remote), context summarisation and offloading, shell access in your sandbox, persistent memory and human-in-the-loop approvals. It is model-agnostic for any tool-calling LLM and builds on LangGraph, with tracing, evals and deployment through LangSmith.; rLLM: rLLM is an Apache-2.0 framework for training language agents with reinforcement learning. You bring any harness, including 10+ CLI agents such as Claude Code, Codex, mini-swe-agent and OpenCode, or wrap your own LangGraph or OpenAI Agents SDK agent with @rllm.rollout, run it in Docker, Daytona, Modal or local sandboxes, and switch training backends with one flag. The same agent code drives both evaluation and training.

Are there free or open-source options?

Yes: 6 open source, 2 free or freemium, 1 pricing on the maker's site. Pricing is as each maker states it.

More from evaluating agents

Tools are grouped by what each says it does. Missing one? Submit it free.