Self-host Oriveo Community Edition
v1.1.0Multi-model AI chat client with bring-your-own-key support
- Stars
- 550
- Port
- 3001 (Next.js web client development and production server)
What is Oriveo Community Edition?
Oriveo Community Edition is a bring-your-own-key AI chat application for iPhone, Android, and browsers, with a Mac version in progress. It works with fifteen major providers and any compatible endpoint such as local servers like Ollama, LM Studio, llama.cpp, and vLLM. The browser version is a Next.js app you run on your own machine; it keeps conversations, notes, folders, skills, and API keys in the browser's IndexedDB without requiring an account. Mobile apps encrypt data in the system keychain and connect directly to providers. Capabilities include streaming chat with reasoning, citations, file attachments, per-provider model settings, relay connections for custom endpoints, subscription sign-in for ChatGPT and Grok, reusable skills with reference documents, MCP tool integration, organized notes and folders, cross-check with a second model, persistent memory facts, per-message cost tracking, image generation, encrypted backups, and sixteen languages with full RTL support for Arabic. Licensed under AGPL-3.0-or-later.
Should you self-host Oriveo Community Edition?
Oriveo Community Edition scores 53/100 on selfhost.directory (how scoring works) and ranks #18 of 69 in AI Chat. It has 550 GitHub stars.
It shipped 2 stable releases in the past year. The latest, v1.1.0, came out on 23 September 2026. New versions land roughly every 2 weeks.
Setup is moderate: expect some configuration beyond a single command. It is AGPL-3.0-licensed and written mostly in Swift.
Its closest alternative on selfhost.directory is openhands (87/100, 92 068 stars). It scores higher overall, so compare the two before you pick. See Oriveo Community Edition vs openhands side by side.
Features
- Bring Your Own Key (BYOK)
- Cost Tracking
- Cross-check
- Encrypted backups
- Image Generation
- Local-First Storage
- Local model server discovery
- MCP Tools
- Memory
- Multi-model chat
- Notes and folders
- Relay connections
- Skills
- Streaming chat with reasoning
- Subscription sign-in
Oriveo Community Edition README
FAQ
Which languages is the interface available in?
Sixteen: Arabic, German, English, Spanish, French, Hindi, Indonesian, Japanese, Korean, Brazilian Portuguese, Russian, Thai, Turkish, Vietnamese, Simplified Chinese, and Traditional Chinese. Arabic gets full right-to-left layout.
Is there a macOS app?
A native macOS client is in development and will arrive in the coming months. Until then the web client works as a desktop app in any browser, and the iOS build runs on Apple silicon Macs from Xcode.
How is Community Edition different from the Oriveo app on the App Store?
The store apps are Oriveo, a proprietary product that adds an account, cross-device cloud sync, usage insights, and models Oriveo pays for. Community Edition has none of that.
Can I self-host Oriveo?
Yes. The web client is the only part with a server side and stores neither keys nor messages. Point it at a model server on your own hardware and self-host the catalog with NEXT_PUBLIC_BACKEND_URL.
Does it work with Ollama, LM Studio or llama.cpp?
Yes. Add a Relay connection pointing at any OpenAI-, Anthropic-, or Gemini-compatible server including llama.cpp, Ollama, LM Studio, vLLM, Open WebUI. iOS and Android find them on the local network via mDNS.
Do my conversations go through an Oriveo server?
No. iOS and Android call the provider directly. On the web most requests pass through the Next.js server serving the app — your own machine when you run it locally — because most provider APIs refuse a browser call.
Is Oriveo a free, open-source ChatGPT alternative?
The client is open source with nothing to subscribe to and no part held behind a payment. You pay the model provider's list price for requests you make, billed by them on the account the key belongs to.
Is Oriveo a BYOK client for OpenAI, Claude, Gemini and OpenRouter?
Yes, you create an API key in a provider's own console and paste it into Oriveo. Requests are billed by that provider at its list price; Oriveo is the client, not a reseller.
More in AI Chat
os1OS1 is a self-hosted, open-source AI platform with autonomous agents, deep research, real-time collaborative chats, and a PWA workspace. Full data control, extensible.
OuroborosA locally-run AI agent that preserves its identity across sessions, spawns specialist sub-agents, and rewrites its own codebase.
OvertChatSelf-hosted AI chat with local models, bundled voice/search, multi-user accounts, native mobile/desktop apps, and portable SQLite database.
OwlySelf-hosted AI support agent unifying WhatsApp, Email, and Phone with cross-channel identity, knowledge base, automation, and tickets.
parlantOpen-source, self-hosted conversational harness for customer-facing AI agents: guidelines, journeys, canned replies and tools matched per turn by a FastAPI server.
PerplexiBotPerplexiBot is a self-hosted Discord bot for AI web research using GPT 3.5 or Ollama models with SearXNG. Runs via Docker Compose.
PHOBOSSelf-hosted AI OS running LLMs, image/video generation, web browsing, audio, and tasks locally with no cloud.
pinchchatA self-hosted webchat UI for OpenClaw agents with real-time tool call visualization, live streaming, and a GPT-like session sidebar.
PocketRisuPocketRisu is a self-hosted, open-source AI roleplay chat platform that runs on your hardware and connects to multiple LLM providers via a web browser.
PrivateDocBotPrivateDocBot is a self-hosted, open-source chatbot for querying PDF documents locally using LLMs like Llama 2 via Chainlit.
profclawRun AI agents on your hardware with this open-source engine. 35 model providers, 72 tools, 22 chat services. Three sizes from tiny to full-featured.
Project N.O.M.A.D.Open-source, self-hosted offline knowledge and education server: Wikipedia, maps, Khan Academy courses and optional local AI, all managed from one Docker dashboard.



0 comments