Alternatives / Poe

9 Best Open Source Poe Alternatives in 2026

Looking for an open source Poe alternative? We compared 9 open source AI chat interfaces and desktop clients by license, model support, local models, self-hosting, and privacy. They let you chat with many models in one place using your own API keys or local models, and several use licenses that are not standard open source.

Maxime DERAME's profile

Written by Maxime DERAME

Last updated:

Best Poe alternatives at a glance

AlternativeBest forLicense
Open WebUISelf-hosted chat for local and cloud models (custom license)Open WebUI License; older code BSD-3-Clause / MIT
LobeChatTeams of AI agents (source available)LobeHub Community License
AnythingLLMChat with your documentsMIT
Cherry StudioDesktop client for 300+ models (AGPL-3.0 Community Edition)AGPL-3.0 Community Edition
LibreChatMulti-user team deploymentsMIT
JanRunning models locally on your desktopApache-2.0
5ireDesktop assistant with MCP (source available)Modified Apache-2.0 (source available)
FullmoonPrivate offline LLMs on Apple devicesMIT
ZolaSimple multi-model chat app (small project)Apache-2.0

How we chose these Poe alternatives

We looked for open-source tools that overlap with Poe's core: one interface to chat with many AI models. We verified each project's license, recent activity, stars, and self-hosting in its repository. Poe is a hosted service that provides access to models for a subscription, so these tools instead connect to your own API keys or local models, and we flag source-available licenses and projects with slow development. See our methodology for the full criteria.

Important: you bring your own models and keys

Unlike Poe, none of these include model access. You connect your own API keys from providers such as OpenAI, Anthropic, or Google, or run local models, and you pay those providers directly. Local inference needs reasonably powerful hardware.

Important: several licenses are not standard open source

Open WebUI uses its own Open WebUI License, a BSD-3-Clause-based license with a branding requirement. LobeChat uses the LobeHub Community License, and 5ire uses a modified Apache-2.0 license, both source available. Cherry Studio's Community Edition is AGPL-3.0, with a separate commercial license for other uses.

Closest to Poe

Open WebUI and LibreChat are the closest as web chat interfaces that support many providers, with accounts and multi-user access. Cherry Studio and 5ire are desktop clients that connect to many providers, and Jan and Fullmoon focus on running models locally.

License details

AnythingLLM, LibreChat, and Fullmoon are MIT. Jan and Zola are Apache-2.0, Cherry Studio is AGPL-3.0 for its Community Edition, and the others use the custom licenses described above.

Maintenance status

Open WebUI, LobeChat, AnythingLLM, Cherry Studio, LibreChat, and Jan were updated within days of this update. Zola's last commit was in December 2025, and Fullmoon's in May 2025, so their development has slowed.

Why look for a Poe alternative?

Poe is a proprietary hosted service: your conversations pass through its servers, access to models is limited by its subscription and compute points, and it decides which bots and models are available. Open-source alternatives let you use your own API keys or local models, keep chats on your machine or server, and avoid subscription caps, at the cost of paying providers directly or running models yourself.

#1

Open WebUI

Self-hosted AI platform for local and cloud language models.

Open WebUI provides a unified interface for Ollama, OpenAI-compatible APIs, Anthropic, and other providers, with document RAG, web search, tools, multimodal input, user management, and extensions. Current code uses the Open WebUI License with branding restrictions.

153.9K22.5KOpen WebUI License; older code BSD-3-Clause / MITSelf-hosted

Pricing: Free to self-host; current license includes branding restrictions beyond traditional permissive licenses.

  • Excellent self-hosting and Ollama integration
  • Local and cloud models, RAG, web search, tools, and multimodal support
  • Multi-user support and large community
  • Current license includes branding restrictions
  • Current releases are not purely BSD-3-Clause
  • Team deployments require infrastructure
#2

LobeChat

Platform for building and operating teams of AI agents.

LobeChat, now LobeHub, is a platform for building and running teams of AI agents on long-running tasks and automated workflows. It includes multi-agent coordination, a large skill library, memory, pages, projects, schedules, and messaging gateways. It is licensed under the LobeHub Community License, based on Apache-2.0 with additional commercial conditions.

83K16KLobeHub Community LicenseSelf-hosted

Pricing: Self-hostable; hosted cloud services may be offered separately.

  • Multi-agent coordination with parallel execution
  • Large skill library with memory and scheduling
  • Workspace features and IM gateway integrations
  • Source available, not standard open source
  • Commercial license needed to distribute derivative works
  • Platform oriented rather than a simple desktop coworker
#3

AnythingLLM

Local-first AI workspace for documents, models, and agents.

AnythingLLM is an MIT-licensed local-first and self-hostable AI workspace with local or cloud models, document ingestion, vector search, agents, multi-user workspaces, and a developer API.

66.7K7.4KMITSelf-hosted

Pricing: Free and open source under MIT with desktop and self-hosted deployments.

  • MIT licensed and no mandatory account
  • Desktop, local models, document chat, RAG, agents, and API
  • Multi-user workspaces
  • More focused on document workflows than general Claude use
  • Local inference requires suitable hardware
  • Setup is more involved than a hosted chatbot
#4

Cherry Studio

Cross-platform desktop AI client for many model providers.

Cherry Studio is an AGPL-3.0 Community Edition desktop AI assistant for Windows, macOS, and Linux. It combines model selection, chat, knowledge bases, agents, MCP servers, documents, model comparison, and local conversation storage.

52.3K5KAGPL-3.0 Community Edition

Pricing: Free and open source Community Edition; external model API costs may apply.

  • Large provider and model selection
  • BYOK, local models, agents, MCP, knowledge bases, and document analysis
  • Cross-platform local conversation storage
  • Desktop-focused
  • Many models require external APIs
  • Large feature set can be more complex than Claude
#5

LibreChat

Self-hosted MIT multi-provider AI chat interface.

LibreChat is an MIT-licensed self-hostable chat interface supporting Anthropic, OpenAI, Gemini, Azure, local models, custom agents, files, tools, web search, code execution, model comparison, and multi-user access.

45.2K9.3KMITSelf-hosted

Pricing: Free and open source under MIT; API provider and infrastructure costs may apply.

  • MIT licensed and multi-provider
  • Self-hosted chat, agents, files, tools, and model comparison
  • Familiar interface with multi-user support
  • Requires API configuration
  • Local models need separate infrastructure
  • Administration is more involved than using Claude directly
#6

Jan

Open-source desktop assistant for local and cloud AI models.

Jan is an Apache-2.0 desktop AI assistant designed to run models such as Llama, Qwen, Mistral, and DeepSeek locally while also supporting cloud providers.

44.8K3.1KApache-2.0

Pricing: Free and open source under Apache-2.0; cloud model API costs may apply.

  • Runs locally and offline
  • Apache-2.0 with local model management
  • Multiple cloud providers, desktop workflow, and strong privacy
  • Performance depends on hardware
  • Large models require significant RAM or GPU resources
  • Cloud capabilities still require third-party APIs
#7

5ire

Cross-platform desktop AI client with MCP and knowledge bases.

5ire is a desktop AI assistant, licensed under a modified Apache-2.0 with additional commercial conditions (source available), for multiple providers, MCP servers, local knowledge bases, document RAG, reusable prompts, cost tracking, and searchable conversations.

5.4K432Modified Apache-2.0 (source available)

Pricing: Free Community Edition with additional terms; a commercial license is required for some uses. Cloud models require provider API keys.

  • Multiple providers and MCP support
  • Local knowledge base and document RAG
  • Prompt library, cost tracking, and cross-platform desktop clients
  • Not standard open source: commercial license required for some uses
  • Primarily a client rather than a complete AI stack
  • Cloud models require API keys
#8

Fullmoon

Lightweight local AI assistant optimized for Apple devices.

Fullmoon is an MIT-licensed local AI assistant that runs compatible language models entirely on iPhone, iPad, Mac, and Vision Pro using Apple's hardware acceleration.

2.3K222MIT

Pricing: Free and open source under MIT; compatible local models run on supported Apple hardware.

  • Runs completely locally and offline
  • Private conversations and MIT license
  • Optimized for iPhone, iPad, Mac, and Apple Silicon
  • Apple devices only
  • Last commit in May 2025 and last release in January 2025, so development has slowed
#9

Zola

Self-hosted Apache-2.0 multi-model AI web chat.

Zola is an Apache-2.0 web chat interface for OpenAI, Anthropic, Gemini, Mistral, OpenRouter, and local Ollama models, with self-hosting and bring-your-own-key support.

1.5K297Apache-2.0Self-hosted

Pricing: Free and open source under Apache-2.0; provider and infrastructure costs may apply.

  • Apache-2.0 and self-hosted
  • Multi-model, Claude, OpenRouter, and Ollama support
  • Clean web interface with BYOK
  • Small project with a last commit in December 2025
  • Fewer features than the larger chat platforms

Compare Poe alternatives

AlternativeTypeLicenseSelf-hostedBest for
Open WebUIWeb chat platformOpen WebUI License (BSD-based)YesLocal and cloud models
LobeChatAgent platformLobeHub Community LicenseYesAgent teams
AnythingLLMDesktop and server appMITYesDocuments and RAG
Cherry StudioDesktop clientAGPL-3.0 (Community)Local appMany providers
LibreChatWeb chat platformMITYesTeams
JanDesktop appApache-2.0Local appLocal models
5ireDesktop assistantModified Apache-2.0Local appMCP tools
FullmooniOS and macOS appMITOn-deviceOffline Apple devices
ZolaWeb chat appApache-2.0YesSimple multi-model chat

Which one should you choose?

Want a self-hosted chat for local and cloud models

Open WebUI connects local and cloud models with extensibility, under a custom license that includes a branding requirement.

Open WebUI

Want a multi-user chat for a team under MIT

LibreChat supports many providers, custom agents, file uploads, and multi-user access, and it is MIT-licensed.

LibreChat

Want to chat with your own documents

AnythingLLM is MIT-licensed and runs as a desktop or self-hosted app with document chat, local models, and agents.

AnythingLLM

Want to run models locally on a desktop

Jan runs open models locally or connects to cloud providers, under Apache-2.0.

Jan

Want a desktop client for many providers

Cherry Studio connects 300+ models from 50+ providers with a local knowledge base, under AGPL-3.0 for its Community Edition.

Cherry Studio

Want private offline LLMs on Apple devices

Fullmoon runs local models on iOS, iPadOS, and macOS, but development has slowed since 2025.

Fullmoon