ChatGPT alternatives: 8 free & open-source picks
Curated, verified, and actually free. No trials, no crippled tiers. Star counts and last-activity dates checked by hand, not scraped and forgotten.
Un escritorio privado de IA para documentos y agentes; instálalo y luego elige modelos locales o el medidor de otro.
licenseMIT
runsyour machine or their cloud
installNative desktop installer, or Docker for a shared/self-hosted server
enginesLocal llama.cpp and imported GGUF models, plus Ollama, LM Studio, LocalAI and numerous cloud providers including OpenAI, Anthropic, Google, Azure, AWS Bedrock, Groq, Mistral, Cohere, and OpenRouter.
dataDesktop data stays in the app's local data directory; the Docker edition persists its server storage volume, including an SQLite database and the default LanceDB vector store. Configured cloud providers receive the prompts and files sent to them.
the catch vs ChatGPTIt includes no frontier-model allowance or first-party voice, image generation, and managed web-research stack, so equivalent capability still needs hardware or paid APIs.
setupA non-expert must choose a model path: download a local model with enough RAM, connect Ollama or LM Studio correctly, or bring and pay for an API key.
facts verified 2026-08-10
Un conmutador de modelos de escritorio con asistentes, archivos, agentes y MCP; trae tus claves o haz sudar a tu laptop.
licenseAGPL-3.0
runson your machine
installNative macOS, Windows, or Linux desktop installer
enginesSupports hundreds of models through providers such as OpenAI, Anthropic, Google Gemini, OpenRouter, Azure, AWS Bedrock, Groq, DeepSeek, Mistral, Ollama, LM Studio, and other OpenAI-compatible services.
dataChats, API keys, assistants, settings, and local knowledge-base data are kept on the device; optional backup can use local files or WebDAV, while configured model providers receive prompts and attachments.
the catch vs ChatGPTCherry Studio provides no included model usage, so matching ChatGPT's best reasoning, image, voice, and research features requires separate providers and bills.
setupThe installer is easy, but useful output requires either a paid provider key or downloading and running a local model that fits the machine.
facts verified 2026-08-10
Un asistente de escritorio local primero con conectores en la nube y herramientas; tu RAM recibe la factura.
licenseApache-2.0
runson your machine
installNative macOS, Windows, or Linux desktop installer
enginesRuns local GGUF models through llama.cpp and Apple-silicon models through MLX, and connects to OpenAI, Anthropic, Google Gemini, Groq, Mistral, Azure, OpenRouter, Hugging Face, and custom OpenAI-compatible APIs.
dataModels, assistants, files, and settings stay in Jan's data folder; threads are stored as local JSON and JSONL files. Cloud providers receive only the conversations or files routed to them.
the catch vs ChatGPTLocal models generally trail ChatGPT's strongest hosted models and multimodal tools, while using comparable cloud models simply moves the cost to API billing.
setupThe first choice is consequential: local models need a sizable download and enough RAM, while cloud models require separately billed API keys.
facts verified 2026-08-10
Un conmutador de modelos autoalojado con agentes, archivos y herramientas; software gratuito, facturas de modelos de pago si usas modelos de pago.
licenseMIT
runsyour server
installOfficial Docker Compose stack
enginesConnects to OpenAI, Anthropic, Google and Vertex AI, Azure OpenAI, AWS Bedrock, Mistral, Groq, custom OpenAI-compatible endpoints, and local backends exposed through compatible APIs.
dataThe default stack stores conversations and accounts in MongoDB, search indexes in Meilisearch, and uploaded or RAG files in local volumes or configured object/vector storage; every configured model provider receives the requests routed to it.
the catch vs ChatGPTLibreChat includes no inference allowance and replaces ChatGPT's managed reliability with Docker, databases, provider keys, security, updates, and backups.
setupIt needs Docker, environment secrets, provider keys, storage, backups, and an admin; the official guide also documents a MongoDB image override because the default image crashes on Apple-silicon Macs.
facts verified 2026-08-10
Un espacio de trabajo multimodelo local primero con archivos, búsqueda, código y personajes; la interfaz asume que te gustan los botones.
licenseMIT
runsyour machine or their cloud
installUse the hosted web app, or deploy the Next.js app yourself
enginesConnects to more than twenty backends, including OpenAI, Anthropic, Google Gemini, OpenRouter, Azure OpenAI, AWS Bedrock, Groq, Mistral, DeepSeek, Ollama, LM Studio, LocalAI, and OpenAI-compatible endpoints.
dataIn the browser edition, provider keys and settings are stored in localStorage and chats, files, personas, and related workspace data in IndexedDB; configured model providers receive submitted content. There is no included cross-device cloud sync.
the catch vs ChatGPTBig-AGI supplies the interface but no model subscription, cross-device sync, or tightly integrated first-party voice and image experience.
setupThe first obstacle is bringing provider keys or a local endpoint; the app warns that browser-stored keys are plain text and protected only by the browser profile.
facts verified 2026-08-10
Un laboratorio de escritorio para modelos locales con chat, documentos y herramientas; gratis para siempre, pero tu hardware ahora es la nube.
licenseproprietary, free
runson your machine
installNative desktop installer or Linux AppImage
enginesRuns downloaded open-weight GGUF and safetensors models locally through llama.cpp and MLX-compatible runtimes, and exposes local OpenAI-compatible APIs.
dataDownloaded models live in LM Studio's local model directory and chats are stored as local JSON conversation files; local inference does not send prompts to a model provider.
the catch vs ChatGPTIt is fundamentally a local-model workstation, not a replacement for ChatGPT's managed frontier reasoning, web research, image generation, voice, and cross-device service.
setupThe first obstacle is hardware: LM Studio recommends 16 GB RAM, requires current supported operating systems and CPU features, and useful models can occupy many gigabytes.
facts verified 2026-08-10
Autoalojamiento con forma de ChatGPT con modelos, archivos, búsqueda y herramientas; el software es gratis, el rol de administrador es tuyo.
licenseOpen WebUI License
runsyour server
installDocker is the recommended path; pip, uv, Kubernetes, and desktop-packaged paths are also documented
enginesConnects natively to Ollama and OpenAI-compatible APIs, with documented support for providers and gateways such as OpenAI, Anthropic, Google, Azure, Groq, Mistral, OpenRouter, and local inference servers.
dataA default single-node install persists accounts and chats in webui.db (SQLite), embeddings in Chroma, and uploads in the Open WebUI data volume; larger deployments can move these to PostgreSQL, Redis, and external vector or object stores.
the catch vs ChatGPTOpen WebUI supplies a strong interface but no models or managed service, so the user must fund inference and administer uptime, security, storage, and backups.
setupThe first obstacle is owning the service: Docker volumes, a model backend or API key, user security, updates, and backups; an unpersisted container loses the data.
facts verified 2026-08-10
Un espacio de trabajo pulido para agentes y archivos; el autoalojamiento es gratis y la inferencia de frontera normalmente no lo es.
licenseLobeHub Community License
runsyour machine or their cloud
installHosted signup, one-click Vercel deployment, or Docker Compose for the server-database edition
enginesSupports more than seventy providers and gateways, including OpenAI, Anthropic, Google Gemini, Azure OpenAI, AWS Bedrock, OpenRouter, Groq, DeepSeek, Ollama, LM Studio, and OpenAI-compatible endpoints.
dataLocal mode keeps chats in browser IndexedDB and supports JSON export; server mode uses PostgreSQL for account and conversation data plus S3-compatible object storage for files. Configured providers receive routed prompts and attachments.
the catch vs ChatGPTLobeHub's polished workspace still includes no frontier inference allowance, and its full server mode adds database, object-storage, authentication, and upgrade work.
setupHosted use still requires model credentials or purchased inference, while serious self-hosting adds PostgreSQL, object storage, authentication, secrets, a domain, and migration from browser-local data.
facts verified 2026-08-10
last updated 2026-08-10 · no votes, no pay-to-list · just what's real
MstyThe desktop core is $0, but the terms limit it to private non-commercial use; paid work needs a license.
| tool | license | running it | platforms | stars | active |
|---|---|---|---|---|---|
| AnythingLLM | MIT | one-click install | web, macos, windows, linux, self-hosted | 64,400 | 2026-08 |
| Cherry Studio | AGPL-3.0 | one-click install | macos, windows, linux | 49,867 | 2026-08 |
| Jan | Apache-2.0 | one-click install | macos, windows, linux | 43,900 | 2026-08 |
| LibreChat | MIT | docker to self-host | web, self-hosted | 41,700 | 2026-08 |
| Big-AGI | MIT | docker to self-host | web, self-hosted | 7,100 | 2026-08 |
| LM Studio | proprietary, free | one-click install | macos, windows, linux | — | — |
| Open WebUI | Open WebUI License | one-click install | web, macos, windows, linux, self-hosted | — | — |
| LobeHub | LobeHub Community License | one-click install | web, self-hosted | — | — |
Se paga la comodidad, los GPTs y no tener que operar la API. If none of that applies to you, any pick above saves $240 a year.
Is there a free alternative to ChatGPT?
Yes: AnythingLLM, Cherry Studio, Jan and 5 more. Every tool on this page is either open source or genuinely free to use long-term: no trials, no crippled tiers.
Should I just build my own ChatGPT?
Our verdict is NO TANTO. El modelo se llama por API. Lo que sobrevive es la cuenta, la memoria y el producto empaquetado. If you'd rather build, the exact one-shot prompt is free at puedovibecodearlo.app/chatgpt.
