LobeHub

Open-source AI agent platform and chat UI supporting every major LLM, plugins, and multi-agent workflows.

Freemium· Free self-hosted (open source); LobeHub Cloud offers Free tier plus paid subscription plans for higher usage limits, extra models, and team features.AgentsOpenAI GPT-4o/o1, Anthropic Claude 3.5/4, Google Gemini, DeepSeek, Mistral, Ollama, and 40+ other providers (bring-your-own-key)

Visit website →

Best for

Developers, indie hackers and small teams who want a self-hosted, multi-provider ChatGPT alternative with plugins, agents and MCP support they can extend and keep on their own infrastructure.

Skip if

Non-technical users who just want a ready-made subscription chatbot with no keys or setup, or enterprises needing SOC2-grade managed hosting with strict SLAs.

LobeHub (formerly LobeChat) is an open-source AI conversation and agent-orchestration platform that gives individuals and teams a polished, ChatGPT-style interface layered over dozens of model providers. Rather than locking users into one vendor, LobeHub lets you plug in API keys for OpenAI, Anthropic, Google, DeepSeek, Mistral, Groq, xAI, Ollama and roughly forty other backends, then switch models per conversation. The project has grown from a single-user chat UI into a broader 'Chief Agent Operator' framework where reusable agents, shared memory, scheduled runs, and MCP-compatible plugins let a small team coordinate parallel AI workflows. A marketplace ships thousands of community-authored agent presets and prompts, and the plugin system now exposes over 10,000 tools including web search, code execution, image generation, file parsing, and third-party APIs. Common workflows include running a personal ChatGPT alternative that keeps history in your own database, building customer-support or research agents that persist structured memory, orchestrating multi-agent 'groups' that collaborate on content, and self-hosting a compliant chat gateway for a company that wants staff to use frontier models without shipping data to a SaaS. Deployment ranges from a one-click Vercel or Docker install to Kubernetes for larger fleets, and the hosted LobeHub Cloud tier offers a managed option with syncing, model credits, and premium agents for users who do not want to run their own instance.

Editor's take

LobeHub is the most polished open-source chat frontend I keep coming back to — it feels closer to a product than most self-hostable UIs, and the plugin/MCP ecosystem plus model-provider breadth make it a great home base if you already juggle OpenAI, Anthropic and a local Ollama box. The recent pivot toward agent orchestration is promising but still catching up to purpose-built agent frameworks.

— The AI Tool Bible editorial team

Pros

✅ Truly model-agnostic: 40+ providers including local Ollama, so you can compare GPT, Claude, Gemini and open models in one UI
✅ Fully open source (LobeHub Community License) with 80k+ GitHub stars and an active release cadence
✅ One-click self-hosting on Vercel, Docker, or your own Postgres, keeping conversation data under your control
✅ Rich plugin and MCP ecosystem with 10k+ tools for web search, code execution, image gen and file handling
✅ Agent marketplace with thousands of pre-built prompts and personas you can fork and customize
✅ Voice conversation, vision, artifact rendering and PWA-quality UI on desktop and mobile
✅ Team-oriented features (agent groups, shared pages, scheduled runs, structured memory) push it beyond a solo chat client

Cons

⚠️ You bring your own API keys and pay the underlying model bills — no bundled inference on the self-hosted edition
⚠️ Setting up authentication, database, S3 storage and provider keys for multi-user self-hosting has a real learning curve
⚠️ Agent 'groups' and multi-agent orchestration are newer and less mature than dedicated agent frameworks like LangGraph or CrewAI
⚠️ Community License restricts certain commercial/multi-tenant hosting scenarios — not a pure MIT/Apache project
⚠️ Cloud tier pricing and quotas change frequently and can be less transparent than the open-source install
⚠️ Rapid feature churn occasionally ships regressions between minor versions

Use cases

Self-hosted ChatGPT alternativeMulti-provider LLM comparisonCustom agent and persona marketplaceMCP plugin host and tool routerTeam knowledge assistant with shared memoryVoice and vision conversational UILocal Ollama chat frontendScheduled agent workflowsPrompt engineering workbench