Google PageRank for AI agents. 25,000+ tools indexed.

agentbox-sdk MCP Server

TwillAI/agentbox-sdk

Score: 68.7 Rank #4316 Agent Framework
[![AgentRank](https://agentrank-ai.com/api/v1/badge/TwillAI--agentbox-sdk)](https://agentrank-ai.com/tool/TwillAI--agentbox-sdk/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of TwillAI/agentbox-sdk? Claim this listing →

The open-source TypeScript SDK for running AI coding agents in sandboxes. One unified API — swap agents and infrastructure providers without changing your code.

Add AgentRank to Claude Code Discover and compare tools like TwillAI/agentbox-sdk — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

TwillAI/agentbox-sdk is a TypeScript tool. The open-source TypeScript SDK for running AI coding agents in sandboxes. One unified API — swap agents and infrastructure providers without changing your code. Topics: agent, agents, llm, mcp.

Ranked #4316 out of 24846 indexed tools.

Ecosystem

TypeScript No license
agentagentsllmmcp

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 164

164 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 50%

5/10 issues closed → decent issue management

Contributors 10% 3

3 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 18
Description Detailed
License None

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Freshness high impact

Last commit was 40 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for TwillAI/agentbox-sdk
[![AgentRank](https://agentrank-ai.com/api/v1/badge/TwillAI--agentbox-sdk)](https://agentrank-ai.com/tool/TwillAI--agentbox-sdk/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/TwillAI--agentbox-sdk/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/TwillAI--agentbox-sdk" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="TwillAI/agentbox-sdk"></script>

Matched Queries

topic:mcp

From the README

# AgentBox

[Live demo](https://agentbox-demo-175164121374.us-west1.run.app/)

Run coding agents inside sandboxes. One API, any provider.

Unlike wrappers that shell out to CLIs in non-interactive mode (e.g. `claude --print`), AgentBox launches each agent as a **server process** inside the sandbox and communicates over WebSocket or HTTP. This preserves the full interactive capabilities of each agent — approval flows, tool-use control, streaming events.

```ts
import { Agent, Sandbox } from "agentbox-sdk";

const sandbox = new Sandbox("local-docker", {
  workingDir: "/workspace",
  image: process.env.IMAGE_ID!,
  env: { ANTHROPIC_API_KEY: process.env.ANTHROPIC_API_KEY! },
});

await sandbox.findOrProvision();

const run = new Agent("claude-code", {
  sandbox,
  cwd: "/workspace",
  approvalMode: "auto",
}).stream({
  model: "sonnet",
  input: "Create a hello world Express server in /workspace/server.ts",
});

for await (const event of run) {
  if (event.type === "text.delta") process.st
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.