VibeAround
UnclaimedCode with your local AI agent from anywhere, through chat or web terminal.
Visit WebsiteFreemiumVisit Website
TL;DR - VibeAround
- Access local AI coding agents via IM apps or a web terminal.
- Seamlessly hand over coding sessions between chat and terminal.
- Supports multiple AI agents and IM platforms with a plugin architecture.
Pricing: Free plan available
Best for: Growing teams
Pros & Cons
Pros
- Highly flexible access to AI agents from various devices and platforms.
- Seamless context transfer between different interaction modes (chat vs. terminal).
- Simplified setup and configuration with a wizard.
- Extensible through a plugin architecture for agents and channels.
- Supports concurrent use of multiple agents across different channels.
Cons
- Requires local setup and management of AI agents and VibeAround application.
- Prerequisites include Rust, Node.js, and Bun, which might be a barrier for some users.
- Relies on third-party AI agents, so functionality is dependent on their capabilities.
Key Features
Chat with local AI agents from Telegram, Slack, Feishu, Discord, WeChat, DingTalk, WeCom, QQFull shell web terminal with on-screen command pad for mobileBidirectional session handover between terminal and IMSwitch AI agents mid-conversation without restartingLive preview of dev servers and rendered Markdown/HTML via short-lived linksOne-click setup wizard for agents, channels, and tunnel providersSupport for multiple AI agents including Claude Code, Gemini CLI, Codex CLI, Cursor CLI, Kiro CLI, Qwen Code, OpenCodeBuilt-in tunnels (ngrok, localtunnel, Cloudflare) for remote access
Pricing Plans
Free TrialFree
$0 USD per month
- Unlimited public/private repositories
- Dependabot security and version updates
- 2,000 CI/CD minutes/month (Free for public repositories)
- 500MB of Packages storage (Free for public repositories)
- Issues & Projects
- Community support
- GitHub Copilot Access
- GitHub Codespaces Access
Team
$4 USD per user/month
- Everything included in Free
- Access to GitHub Codespaces
- Repository rules
- Multiple reviewers in pull requests
- Draft pull requests
- Code owners
- Required reviewers
- Pages and Wikis
- Environment deployment branches and secrets
- 3,000 CI/CD minutes/month (Free for public repositories)
- 2GB of Packages storage (Free for public repositories)
- Web-based support
- GitHub Secret Protection
- GitHub Code Security
Enterprise
$21 USD per user/month
- Everything included in Team
- Data residency
- Enterprise Managed Users
- User provisioning through SCIM
- Enterprise Account to centrally manage multiple organizations
- Environment protection rules
- Repository rules
- Audit Log API
- SOC1, SOC2, type 2 reports annually
- FedRAMP Tailored Authority to Operate
What is VibeAround?
VibeAround provides a flexible interface to interact with your local AI coding agents (like Claude Code, Codex, Gemini CLI, Cursor) from various platforms. It allows developers to chat with their AI agent through popular instant messaging applications such as Telegram, Slack, Feishu, and Discord, enabling full coding capabilities directly within chat bubbles. Alternatively, users can access a browser-based web terminal, compatible with tmux, for a more traditional coding environment, complete with an on-screen command pad for mobile use.
The product is designed for developers who want seamless access to their AI coding assistants regardless of their location or device. It features bidirectional session handover, allowing users to move live coding sessions between IM and terminal while preserving context. VibeAround is built as a lightweight, all-in-one Tauri desktop application with a GUI for configuration and service management, supporting a plugin architecture for agents and IM channels. It streamlines setup with a one-click wizard that handles dependencies, credentials, and tunnel providers, minimizing manual configuration.
Reviews
Be the first to review VibeAround
Your take helps the next buyer. Verified LinkedIn reviewers get a badge.
Write a reviewBest VibeAround Alternatives
Top alternatives based on features, pricing, and user needs.
Explore More
VibeAround FAQ
What is the Agent Client Protocol (ACP) and why is it important for VibeAround?
ACP is a standard protocol over stdio that all supported AI agents in VibeAround communicate through. This standardization allows VibeAround to easily integrate new agents and ensures a consistent experience when switching between different AI assistants, as they all 'speak the same language' to VibeAround's core.
How does VibeAround ensure the security of public URLs for the web terminal and live preview?
VibeAround implements token-gated public URLs for its web terminal and live preview features. This means that while the URLs are publicly accessible, they require authentication to open, ensuring that only authorized users (you) can access your sessions and shared content.
Can I use VibeAround with an AI agent that is not explicitly listed as supported?
VibeAround is designed with a plugin architecture, and agents communicate via the Agent Client Protocol (ACP) over stdio. If an AI agent can be configured to communicate using ACP, it may be possible to integrate it, or even build a custom plugin for it using the provided SDK, even if it's not officially listed.
What is the purpose of the 'Skill + MCP auto-injection' feature?
On startup, VibeAround automatically writes its own skills (defined in SKILL.md) and its MCP (Multi-Channel Protocol) endpoint into the global configuration of each enabled AI agent. This allows the agents to automatically discover and understand VibeAround's capabilities and how to interact with it, streamlining the integration.
How does VibeAround handle the display of messages from AI agents across different instant messaging platforms?
VibeAround uses native rendering for each channel. This means that each IM channel plugin utilizes the platform's own SDK (e.g., Telegraf for Telegram, Lark SDK for Feishu, Slack Bolt for Slack). This approach ensures that messages from AI agents are rendered in the richest format supported by each specific platform, rather than being limited by a lowest-common-denominator display layer.
Source: github.com