Logo
Deploy Now

SaaS Alternative

Perplexity Claude

Categories

Developer Tools Productivity AI Collaboration LLM Machine Learning Chatbot Artificial Intelligence

Stars

82,070

Forks

15,840

Watchers

307

Developer links

Last Updated: 08-28-2026 06:42 PM (UTC)

LobeHub

With over 82,000 GitHub stars and 700,000+ downloads, LobeHub has evolved from its origins as LobeChat into a comprehensive multi-agent AI collaboration platform where humans and autonomous agent teams co-evolve. The platform's Agent Harness architecture functions as an operating system between AI models and applications, handling prompt presets, tool orchestration, lifecycle hooks, planning, filesystem access, and sub-agent management across 25+ model providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Mistral, Groq, AWS Bedrock, Azure OpenAI, and local models through Ollama. Agent Groups enable sophisticated collaboration with sequential, parallel, iterative, and debate orchestration modes, allowing multiple specialized agents to tackle complex workflows simultaneously. The Agent Builder creates production-ready agents from natural language descriptions with auto-configuration, drawing from a marketplace of 505+ pre-built agents and 10,000+ MCP-compatible skills and plugins. Pages provide collaborative document editing with multi-agent co-authoring, while Schedules automate agent runs around the clock without human supervision. The knowledge base leverages PostgreSQL with pgvector for RAG-powered retrieval, and Personal Memory gives agents transparent, editable context that evolves through continual learning. The full self-hosted stack deploys via Docker Compose with PostgreSQL, Redis, RustFS for S3-compatible storage, and SearXNG for private web search, all configurable through environment variables. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. LobeHub Community licensed.

LobeHub
LobeHub
LobeHub
LobeHub
LobeHub
LobeHub
LobeHub

Benefits

  • Multi-Agent Team Orchestration
  • Deploy Agent Groups with sequential, parallel, iterative, and debate modes to coordinate multiple specialized AI agents tackling complex workflows collaboratively in real time.
  • Model-Agnostic Universal Access
  • Connect to 25+ AI providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Mistral, Groq, and local models via Ollama from a single unified interface.
  • RAG-Powered Knowledge Integration
  • Build knowledge bases using PostgreSQL with pgvector for vector similarity search, enabling agents to retrieve and reason over your documents, files, and organizational data.
  • Full Self-Hosted Data Sovereignty
  • Deploy the complete stack via Docker Compose including PostgreSQL, Redis, RustFS, and SearXNG with full control over your data, API keys, and infrastructure.

Features

  • Agent Builder
  • Create custom AI agents from natural language descriptions with auto-configuration for system prompts, model selection, and capability setup, plus 505+ marketplace agents.
  • 10,000+ MCP Skills
  • Extend agent capabilities with over 10,000 Model Context Protocol compatible tools and plugins covering web search, file operations, APIs, and developer workflows.
  • Collaborative Pages
  • Write and refine documents in a multi-agent workspace where agents co-author content with rich markdown editing, live preview, and knowledge base integration.
  • Scheduled Agent Workflows
  • Automate recurring tasks by scheduling agent runs to execute at designated times, delivering results and reports without requiring continuous human presence.
  • Personal Agent Memory
  • Agents build transparent, editable memory profiles through continual learning, adapting behavior to user preferences with full white-box visibility and control.