vibekit  by superagent-ai

SDK for running coding agents in secure sandboxes

Created 4 months ago
1,242 stars

Top 31.8% on SourcePulse

GitHubView on GitHub
Project Summary

VibeKit is an SDK designed for securely running and integrating various coding agents, including Claude Code, OpenAI Codex, Gemini CLI, and SST Opencode, into applications and workflows. It targets developers and teams looking to leverage AI for code generation, automation, and testing within isolated, cloud-based environments, offering a unified interface for diverse LLM-powered coding tools.

How It Works

VibeKit provides a drop-in SDK that abstracts the complexities of interacting with different coding agents and sandbox environments. It focuses on secure code execution through customizable sandboxes, enabling developers to generate and run code safely. The architecture supports cloud-based execution with plans for local support, and it emphasizes features like streamed output for real-time UIs, prompt history, and OpenTelemetry integration for observability.

Quick Start & Requirements

  • Installation: Primarily via SDK integration into existing applications.
  • Prerequisites: Cloud-based execution environments (e.g., E2B with Daytona, Modal, Fly.io). Local execution is planned.
  • Resources: Specific resource requirements depend on the chosen sandbox provider and agent complexity.
  • Links: Website, Docs, Discord

Highlighted Details

  • Supports multiple coding agents: Claude Code, OpenAI Codex, Gemini CLI, SST Opencode.
  • Features secure sandboxing for safe code execution.
  • Offers cloud-based execution with GitHub automation capabilities.
  • Provides streamed output for real-time UI integration.

Maintenance & Community

  • The project is maintained by Superagent Technologies Inc.
  • Community engagement is encouraged via Discord.

Licensing & Compatibility

  • License: MIT.
  • Compatibility: Permissive MIT license allows for commercial use and integration into closed-source applications.

Limitations & Caveats

Currently, VibeKit focuses on cloud-based execution, with local execution support slated for future development. The range of supported sandbox runtimes is expanding, with E2B, Modal, and Fly.io mentioned as initial integrations.

Health Check
Last Commit

3 days ago

Responsiveness

1 day

Pull Requests (30d)
24
Issues (30d)
8
Star History
136 stars in the last 30 days

Explore Similar Projects

Starred by Jared Palmer Jared Palmer(Ex-VP AI at Vercel; Founder of Turborepo; Author of Formik, TSDX), Shawn Lewis Shawn Lewis(Cofounder of Weights & Biases), and
4 more.

arrakis by abshkbh

0.5%
572
Sandboxing solution for AI agent code execution and computer use
Created 1 year ago
Updated 3 months ago
Starred by Jeff Hammerbacher Jeff Hammerbacher(Cofounder of Cloudera), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
5 more.

code-interpreter by e2b-dev

0.5%
2k
SDK for running AI-generated code in secure cloud sandboxes
Created 1 year ago
Updated 2 weeks ago
Starred by Joe Walnes Joe Walnes(Head of Experimental Projects at Stripe), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
21 more.

E2B by e2b-dev

0.5%
10k
Open-source cloud runtime for AI apps and agents
Created 2 years ago
Updated 1 day ago
Feedback? Help us improve.