#1
A tool for downloading and running open large language models locally through a command line and REST API, with Docker support and many integrations.
- GitHub stars
- 187k
- Last commit
- yesterday
- Latest release
- v0.40.16
- Licence
- MIT
- Self-hosted
- Yes
ollama.com
Ollama makes it straightforward to run open large language models on your own machine. You install it on macOS, Windows or Linux, or use the official Docker image, then pull a model and chat with it from the command line. It is written in Go and released under the MIT license, and it builds on the llama.cpp project for inference.
Besides the CLI, Ollama provides a REST API for managing and running models, with official Python and JavaScript client libraries. Models can be imported and customized through a Modelfile, and an online library lists what is available. It can be connected to coding agents and assistants such as Claude Code, OpenCode, Codex and OpenClaw, and many community chat interfaces, including Open WebUI and LibreChat, work with it.
Because models run on your own hardware, Ollama can serve as a self-hosted alternative to cloud assistants such as ChatGPT and Perplexity when privacy, offline use or cost control matter. It is aimed at developers and hobbyists experimenting with open models, and at teams that want to wire local models into their own applications.
Key features
- Run open language models locally from the CLI
- REST API for managing and running models
- Official Python and JavaScript libraries
- Modelfile for customizing and importing models
- Official Docker image
- Integrations with coding agents and chat interfaces
Pricing: Running models locally is free, and the Free plan includes starter cloud credits. Pro costs $20, Max $100 and Team $500 per month with included usage credits; Enterprise is custom.
#2
A Python library and server for fast, memory-efficient LLM inference and serving, with PagedAttention, continuous batching and broad quantization support.
- GitHub stars
- 97k
- Last commit
- yesterday
- Latest release
- v0.33.0rc3
- Licence
- Apache-2.0
- Self-hosted
- Yes
vllm.ai
vLLM is an open-source library for running and serving large language models efficiently. It originated at UC Berkeley's Sky Computing Lab and is now developed by a large community of contributors from academia and industry. It is written in Python and released under the Apache-2.0 license.
Speed comes from techniques such as PagedAttention for attention key-value memory, batching incoming requests continuously, chunked prefill, prefix caching, CUDA and HIP graphs, and optimized attention and mixture-of-experts kernels. It supports many quantization formats, including FP8, INT8, INT4, GPTQ and AWQ, as well as speculative decoding and disaggregated prefill and decode.
On the usability side, vLLM integrates with Hugging Face models and supports parallel sampling, beam search, streaming outputs, structured outputs and tool calling, plus several parallelism modes (tensor, pipeline, data, expert and context) for distributed inference. It targets NVIDIA, AMD and TPU hardware and suits teams that serve open models in production and need high throughput.
Key features
- PagedAttention and continuous batching
- Quantization including FP8, INT8, GPTQ and AWQ
- Speculative decoding support
- Tensor, pipeline and expert parallelism
- OpenAI-compatible API server
- Hugging Face model integration
- Streaming and structured outputs
Pricing: Free and open source under the Apache-2.0 license.
#3
A self-hosted chat interface for local and cloud language models, supporting Ollama and OpenAI-compatible APIs, with RAG, user roles and a plugin system.
- GitHub stars
- 158k
- Last commit
- yesterday
- Latest release
- v0.13.3
- Self-hosted
- Yes
openwebui.com
Open WebUI is a self-hosted web interface for working with large language models. It connects to Ollama for local models and to any OpenAI-compatible endpoint, so one deployment can front LM Studio, Groq, Mistral, OpenRouter, vLLM and similar backends side by side. It is designed to keep working fully offline when you rely only on local models.
Administrators get role-based access control with user groups and per-group permissions, which suits shared team or household installs. Beyond chat there is retrieval-augmented generation over your documents, custom models that bundle instructions, tools and knowledge into agents, and an extension system made of filters, actions, pipes, tools and skills. External services attach through MCP, MCPO and OpenAPI tool servers, and an optional Open Terminal feature gives agents a filesystem to work in.
You can install it with pip, uv or Docker, or deploy it to Kubernetes using kubectl, kustomize or Helm, and container images are tagged for bundled Ollama and for CUDA. The project lists an enterprise plan for organizations that want vendor support. Its license is listed as custom rather than a standard one, so review the terms before reselling or rebranding it.
Key features
- Connects to Ollama and OpenAI-compatible APIs
- Role-based access control with user groups
- Retrieval-augmented generation over your own documents
- Plugin system with filters, tools and pipes
- MCP and OpenAPI tool server support
- Custom agents combining models, tools and knowledge
- Install via pip, Docker or Kubernetes
Pricing: Free to self-host; an enterprise plan is available through the vendor's sales team.
#4
A self-hosted AI gateway that connects many upstream model services and exposes one consistent API, with routing, access control, usage tracking and a web console.
- GitHub stars
- 52k
- Last commit
- yesterday
- Latest release
- v1.0.0-rc.49
- Licence
- AGPL-3.0
- Self-hosted
- Yes
newapi.ai
New API is an AI gateway you host yourself, built for apps, agents and teams. It lets you plug in upstream model services, present one consistent API to clients, and handle routing, access, usage and cost management centrally. It is written in Go and released under the AGPL-3.0 license.
It can convert between formats so that various LLMs are reachable through OpenAI-compatible, Claude-compatible or Gemini-compatible interfaces. Supported upstreams range from OpenAI, Anthropic and Gemini to Azure OpenAI, AWS Bedrock, Vertex AI, DeepSeek and Qwen, plus other compatible services, and a web console is used for administration.
Typical uses are sharing authorized model access across a team, switching providers without reconfiguring every client, and operating a private multi-model service. The README stresses lawful, authorized use: users must obtain upstream keys legitimately, follow upstream terms, and meet any regulatory obligations if they offer AI services to the public. It suits teams and organizations that need centralized model management.
Key features
- Unified gateway for multiple upstream model services
- OpenAI, Claude and Gemini compatible formats
- Routing, access control and usage tracking
- Cost accounting and usage analytics
- Web console for administration
- Self-hosted private deployment
Pricing: Free and open source under the AGPL-3.0 license.
#5
An open-source AI gateway and Python SDK that lets you call 100+ LLM providers through one OpenAI-style interface, with spend tracking and load balancing.
- GitHub stars
- 63k
- Last commit
- yesterday
- Latest release
- v1.109.1
- Self-hosted
- Yes
- Hosted version
- Available
docs.litellm.ai
LiteLLM is an AI gateway, open source, offering one unified interface for calling more than 100 LLM providers, including OpenAI, Anthropic, Gemini, Bedrock and Azure, using the OpenAI request format. It can be used as a Python SDK inside an application or deployed as a proxy server that serves a whole team or organization. The core is Python with a Rust component, and GitHub lists the license as 'Other'.
The project aims to remove the hassle of handling a separate SDK, login scheme, request format and set of errors for each model. On top of that the gateway provides load balancing, guardrails, spend tracking, virtual keys and an admin dashboard, and it exposes endpoints for chat completions, responses, embeddings, images, audio, batches and reranking.
Because requests keep the OpenAI format, teams can swap providers without rewriting application code. It is self-hosted, with hosted-proxy and enterprise tier options linked in the README, and its topics also reference an MCP gateway and LLMOps. It suits platform and AI engineering teams that need central control over model access, budgets and logging.
Key features
- Unified OpenAI-format interface for 100+ LLMs
- Python SDK and proxy server modes
- Virtual keys and spend tracking
- Guardrails and load balancing
- Built-in admin dashboard
- Endpoints for chat, embeddings, images and audio
Pricing: The open-source gateway can be self-hosted; the README also links hosted proxy and enterprise tier offerings.
#6
An open-source platform that organizes AI agents into continuous operations, with options to self-host through Docker or major cloud platforms.
- GitHub stars
- 85k
- Last commit
- yesterday
- Latest release
- v2.3.2
- Self-hosted
- Yes
lobehub.com
LobeHub describes itself as a Chief Agent Operator that organizes your AI agents into around-the-clock operation. It is designed to take on the hiring, scheduling and reporting for a whole team of agents so that you stay in charge without having to stay online. The project is written in TypeScript, and its GitHub topics point to chat, agent, knowledge base and MCP functionality.
The README groups its features around four ideas: Operator, Create, Collaborate and Evolve, which cover treating agents as the unit of work, scaling new kinds of collaboration networks, and the co-evolution of humans and agents. A plugin ecosystem extends the platform, and the project's topics reference model providers such as OpenAI, Claude, Gemini and DeepSeek.
LobeHub can be self-hosted: the README documents deployment on Vercel, Zeabur, Sealos and Alibaba Cloud, as well as Docker, and describes the environment variables used for configuration. GitHub lists the license as 'Other', so check the repository for the exact terms. It suits individuals and teams who want to run a shared workspace of AI agents on infrastructure they choose.
Key features
- Agents organized into continuous operations
- Scheduling and reporting for agent teams
- Knowledge base, skills and MCP support
- Plugin ecosystem for extending agents
- Docker and cloud platform deployment
- Support for major model providers
Pricing: Free plan with 500,000 monthly credits. Starter costs $12.90, Premium $24.90 and Ultimate $49.90 per month billed monthly, or about $9.90, $19.90 and $39.90 billed yearly; Enterprise Edition is by contact.
#7
An open-source AI engine that runs LLMs, vision, voice, image and video models on your own hardware behind OpenAI-compatible APIs, with no GPU required.
- GitHub stars
- 50k
- Last commit
- yesterday
- Latest release
- v4.12.1
- Licence
- MIT
- Self-hosted
- Yes
localai.io
LocalAI is an open-source AI engine for running models of many kinds, including language, vision, voice, image and video models, on your own hardware. A GPU is not required. It is written in Go and released under the MIT license, was started by Ettore Di Giacinto and is looked after by the LocalAI team.
Its design is a small core with separate backends that are pulled on demand, so nothing unused gets installed. Backends wrap engines such as llama.cpp, vLLM, whisper.cpp, stable-diffusion and MLX, and you can write your own in any language against an open interface. It can run on CPU alone, through Vulkan, or on NVIDIA, AMD, Intel and Apple Silicon hardware.
APIs are drop-in compatible with OpenAI, Anthropic and ElevenLabs across every backend. Multi-user features include API key authentication, user quotas and role-based access, and built-in agents support tool use, RAG, MCP and skills. The project stresses that data stays on your infrastructure. It suits developers and teams who want a private, self-hosted replacement for cloud AI APIs.
Key features
- Runs LLM, vision, voice, image and video models
- Composable backends pulled on demand
- OpenAI, Anthropic and ElevenLabs API compatibility
- Runs on CPU, NVIDIA, AMD, Intel and Apple Silicon
- API key authentication, quotas and role-based access
- Built-in agents with tools, RAG and MCP
Pricing: Free and open source under the MIT license.
#8
An open-source desktop app that acts as a ChatGPT replacement, running local language models offline or connecting to cloud providers, with an OpenAI-compatible local server.
- GitHub stars
- 46k
- Last commit
- yesterday
- Latest release
- v0.8.8
- Self-hosted
- Yes
jan.ai
Jan is an open-source desktop application that serves as a ChatGPT alternative you control. It can download and run language models such as Llama, Gemma, Qwen and GPT-oss from Hugging Face entirely on your own computer, so conversations stay private and work without an internet connection.
When you want more capability than local hardware allows, Jan can connect to cloud models from OpenAI, Anthropic, Mistral, Groq, MiniMax and others from the same interface. You can create custom assistants for specific tasks, and Model Context Protocol support adds agentic abilities. A built-in local server on localhost port 1337 exposes an OpenAI-compatible API, so other applications can use your local models as a drop-in backend.
Jan is built with Rust and Tauri and ships installers for Windows, macOS and Linux in deb and AppImage form. Its license is listed as 'Other' on GitHub, so check the repository terms before redistributing it. It is meant for people who want local AI with a polished interface rather than a command line.
Key features
- Download and run local LLMs from Hugging Face
- Connect to OpenAI, Anthropic, Mistral and Groq
- Custom assistants for specific tasks
- OpenAI-compatible local server
- Model Context Protocol integration
- Installers for Windows, macOS and Linux
Pricing: Free and open source; running local models costs nothing beyond your own hardware, and cloud providers bill you separately.
#9
Ray is an open source framework for managing, executing, and optimizing compute needs, designed to support any AI or ML workload.
- GitHub stars
- 44k
- Last commit
- yesterday
- Latest release
- ray-2.60.0
- Licence
- Apache-2.0
- Self-hosted
- Yes
- Hosted version
- Available
ray.io
Ray is an AI compute engine that consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. It is Python-native and built by developers for developers, designed to orchestrate infrastructure for distributed workloads on any accelerator at any scale.
The platform aims to address the AI Complexity Wall by supporting any AI or ML workload, any data types and model architectures, and heterogeneous GPUs and CPUs with fine-grained scaling. It can scale from a laptop to thousands of GPUs.
Key features
- Supports any AI or ML workload
- Handles multi-modal data processing including images, videos, audio
- Runs distributed training for Gen AI foundation models, time series models, and traditional AI/ML models
- Offers model serving with independent scaling and fractional resources via Ray Serve
- Supports batch inference with heterogeneous compute using CPUs and GPUs
#10
SvelteKit chat interface for large language models that connects to any OpenAI-compatible API and powers HuggingChat.
- GitHub stars
- 11k
- Last commit
- yesterday
- Latest release
- v0.10.0
- Licence
- Apache-2.0
- Self-hosted
- Yes
- Hosted version
- Available
huggingface.co
Chat UI is a chat interface for LLMs built as a SvelteKit application. It is the open source codebase behind HuggingChat on Hugging Face and lets you run a similar conversational front end against models you choose, whether hosted or running locally.
The current version speaks only to OpenAI-compatible APIs, configured through a base URL and a models endpoint. The README lists the Hugging Face Inference Providers router, a llama.cpp server, Ollama through its OpenAI-compatible bridge, OpenRouter and Poe as example backends. Older provider-specific integrations were removed from the main branch but remain available on a legacy branch.
Setup involves creating an .env.local file with the endpoint and key, choosing a database option, and launching the app, with an optional Docker image. The project is written in TypeScript with Tailwind CSS and is licensed under Apache-2.0, making it a base for self-hosted assistants.
Key features
- Chat front end for any OpenAI-compatible API
- Works with llama.cpp, Ollama and OpenRouter
- Hugging Face Inference Providers support
- Configured through a simple .env.local file
- Optional Docker image
- SvelteKit and Tailwind CSS codebase
Pricing: Free and open source under the Apache-2.0 license.
7 more OpenRouter alternatives
- View tool
Use and compare GPT-6, Claude 5, Gemini 3 and more chatbots simultaneously
GPL-3.0vs Poe★ 11k
- View tool

Helicone
AI Infrastructure
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and expe
Apache-2.0vs OpenRouter★ 6.3k
- View tool
AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Inclu
MITvs ChatGPT★ 7.2k
- View tool
LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一
MITvs OpenRouter★ 37k
- View tool

LLM Gateway
AI Infrastructure
Route, manage, and analyze your LLM requests across multiple providers with a unified API
OSSvs Amazon Bedrock★ 1.7k
- View tool

Portkey AI Gateway
AI Infrastructure
A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardra
MITvs Amazon Bedrock★ 13k
- View tool
Independent LLM API price desk: compare model pricing across OpenAI, Anthropic, Google and more.
SaaSvs OpenRouter
OpenRouter alternatives: questions
- What is the best open-source alternative to OpenRouter?
- Ollama is the top-ranked open-source alternative to OpenRouter on Enlisted: A tool for downloading and running open large language models locally through a command line and REST API, with Docker support and many integrations. Other strong options are vLLM, Open WebUI, New API and LiteLLM.
- What are the best commercial alternatives to OpenRouter?
- DeepInfra, Fireworks AI, Portkey, OpenAI API Platform and Together AI are among the hosted, closed-source alternatives to OpenRouter listed on Enlisted, which lists 34 in total. Compare their pricing and features on each tool page.
- Are these OpenRouter alternatives free?
- All 17 are open source, so the code is free to use under its licence, and all of them can be self-hosted on your own server or computer. 9 also offer a paid or managed cloud version if you'd rather not host it yourself.
- How is this list of OpenRouter alternatives ranked?
- By a score built from GitHub stars, star growth over the last 30 days and how recently the code changed. 14 of these projects shipped code in the last 30 days. Data is refreshed daily, and nobody can pay to move up.