xpander.ai  by xpander-ai

Backend-as-a-Service for AI Agents

created 3 months ago
389 stars

Top 73.6% on SourcePulse

GitHubView on GitHub
Project Summary

Xpander.ai provides a Backend-as-a-Service for AI agents, abstracting infrastructure complexities to enable developers to focus on agent logic. It supports framework-agnostic integration, offering tools, memory, multi-agent collaboration, state management, and various triggering mechanisms for production-ready autonomous agents.

How It Works

Xpander.ai acts as a central hub for AI agent operations, abstracting away the complexities of deployment, scaling, and inter-agent communication. It offers a distributed state management system and event streaming capabilities for real-time interactions. The Agent-Graph-System provides API guardrails, enabling the definition and management of dependencies between tool-use actions, enhancing the robustness and security of agent workflows.

Quick Start & Requirements

  • Installation: pip install xpander-sdk (Python), npm install @xpander-ai/sdk (Node.js), npm install -g xpander-cli (CLI).
  • Prerequisites: Python 3.x, Node.js. Requires an Xpander API key for full functionality.
  • Setup: xpander login, xpander agent new, xpander dev for local development. Deployment via xpander deploy.
  • Resources: Official Documentation: https://docs.xpander.ai/, API Reference: https://docs.xpander.ai/api-reference.

Highlighted Details

  • Framework Flexibility: Supports OpenAI ADK, Agno, CrewAI, LangChain, and native LLM APIs.
  • Tool Integration: Offers a comprehensive MCP-compatible tools library and pre-built integrations.
  • State Management: Provides framework-specific local state or distributed state management.
  • Real-time Events: Supports Slackbots, ChatUIs, Agent2Agent communication, and Webhook integrations.

Maintenance & Community

Licensing & Compatibility

  • License: Open-source runtime is under Apache License 2.0. The hosted platform has a commercial license with a free tier.
  • Compatibility: Apache 2.0 runtime is generally compatible with commercial and closed-source applications.

Limitations & Caveats

The hosted platform is commercial, though a free tier is available. Specific details on the scope of the "Commercial" license for the hosted platform are not elaborated in the README.

Health Check
Last commit

1 week ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
33 stars in the last 30 days

Explore Similar Projects

Starred by Wes McKinney Wes McKinney(Author of Pandas), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
14 more.

autogen by microsoft

0.5%
49k
Agentic framework for multi-agent AI applications
created 2 years ago
updated 6 days ago
Feedback? Help us improve.