The best open-source AI chat apps in 2026
The best open-source AI chat apps right now are Open WebUI, Dify and LibreChat, out of 10 we have reviewed. Each is ranked by our rating, with its price, our verdict and who it suits.
Updated Oct 23, 2026 · Ranked from our reviews · How we review
- 1
A self-hosted chat portal with admin controls most paid products lack, from a project that published 159 security advisories in 2026 alone.
Best for: Teams that want a private, multi-user chat portal over local and cloud models.
Price: Free to self-host at any scale with the branding intact. White-labelling above 50 users, and the Terminals add-on, need an enterprise licence priced per seat; prices are not published.
Read our Open WebUI review4.6/5 - 2
Dify gives business teams a complete LLM app builder they can edit themselves, on a licence that only bites when you resell it as a hosted service.
Best for: Teams building internal chatbots and RAG apps that non-engineers will maintain.
Price: Self-hosted Community Edition free (modified Apache 2.0, one workspace). Dify Cloud: Sandbox free (200 one-time message credits), Professional $590/workspace/year, Team $1,590/workspace/year (annual billing, which Dify says saves 17%), Enterprise by quote.
Read our Dify review4.5/5 - 3
A permissively licensed company chat portal with serious agent and MCP features, provided someone on staff is happy to own a YAML file and a MongoDB.
Best for: Companies that want a rebrandable internal ChatGPT alternative across many providers.
Price: Free and open source (MIT). No paid tier; you pay your model providers and hosting.
Read our LibreChat review4.4/5 - 4
Wide reach for wiring AI steps into business systems at a flat self-hosted cost, offset by a security patch cadence no self-hoster can ignore.
Best for: Ops and engineering teams automating business processes that include AI steps.
Price: Fair-code: Community Edition free to self-host under the Sustainable Use License. Billed annually: Cloud Starter €20/month (2,500 executions), Pro €50/month (10,000); self-hosted Business €667/month (40,000); Enterprise custom.
Read our n8n review4.4/5 - 5
AnythingLLM is the shortest path from a folder of PDFs to a private chatbot, but 25 security advisories argue for keeping its server edition behind a login and a VPN.
Best for: Individuals and small teams who want private chat over their own documents.
Price: Desktop and Docker free (MIT); an optional Desktop Pro subscription lifts daily limits on its Magic features (price not published in the docs). Hosted Cloud Basic $50/month, Pro $99/month; Enterprise custom.
Read our AnythingLLM review4.3/5 - 6
A fully open, account-free desktop home for local models that has quietly grown into an agent, so its defaults now matter more than its looks.
Best for: Privacy-minded individuals who want to run open models offline in a desktop app.
Price: Free and open source (Apache 2.0). No paid tier; cloud models use your own API keys.
Read our Jan review4.2/5 - 7
A capable personal AI workstation for people with many API keys, whose security history makes prompt updating non-negotiable.
Best for: Power users who work across many AI providers from one desktop app.
Price: Community Edition free under AGPL-3.0. Cherry Cloud managed models and the Enterprise edition are not publicly priced.
Read our Cherry Studio review4.1/5 - 8
Better looking than any open-source rival, but a licence that bars modified redistribution and a long run of serious advisories make it a riskier server to expose than LibreChat or Open WebUI.
Best for: Individuals and small teams who want an attractive multi-model chat and agent app.
Price: Self-hosting free under the LobeHub Community License. LobeHub Cloud: Free; Starter $12.90/month ($9.90 billed yearly); Premium $24.90 ($19.90 yearly); Ultimate $49.90 ($39.90 yearly). Enterprise Edition by quote.
Read our LobeHub (formerly LobeChat) review4.1/5 - 9
A dazzling demonstration of a voice agent operating real software, built for exploring public data rather than relying on it.
Best for: Journalists, OSINT hobbyists and developers who want to explore live public data, or study how a voice agent can drive an app.
Price: Free and open source under MIT. Voice uses your OpenAI or Gemini API usage; Google 3D tiles are metered.
Read our God's Eye View review3.9/5 - 10
Langflow is the most capable fully MIT visual agent builder left standing, and also one of the most attacked, so treat every instance as something to patch weekly and never expose directly.
Best for: Developers prototyping agents and RAG pipelines who want a visual editor and a permissive licence.
Price: Free and open source (MIT). No official hosted cloud since April 2026; the enterprise route is through IBM, with no published price.
Read our Langflow review3.8/5
More guides
- Best open-source tools to run LLMs locally
- Best open-source AI agent frameworks
- Best open-source RAG tools
- Best open-source LLM fine-tuning tools
- Best open-source AI coding agents
- Best open-source LLM evaluation tools
- Best open-source LLM gateways and observability tools
- Best Claude Code plugins and agent skills