#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 fair-code workflow automation platform that mixes a visual canvas with custom code and AI agent features, for teams connecting apps and automating processes.
- GitHub stars
- 210k
- Last commit
- today
- Latest release
- n8n@2.47.5
- Self-hosted
- Yes
- Hosted version
- Available
n8n.io
n8n is a workflow automation platform for connecting apps, moving data between them and triggering actions without writing a full integration from scratch. Workflows are built on a visual canvas, and when a step needs more logic you can drop in JavaScript or Python and use npm packages. It is often compared with Zapier and Make, but the source is public and it can run on your own infrastructure.
Recent versions put a lot of weight on AI. You can build multi-step agents and LLM workflows that call OpenAI, Anthropic, Google or open-source models, add human approval steps, and inspect what happened afterward. The project advertises over a thousand integrations and a large library of ready-made workflow templates, and you can extend it with your own nodes.
n8n is distributed under a fair-code model: the Sustainable Use License, plus a separate enterprise license for additional features. The code is always visible and can be self-hosted, for example with Docker, but it is not an OSI-approved open-source license, so commercial redistribution is restricted. A managed cloud edition is available if you would rather not run it yourself.
Key features
- Visual workflow canvas with branching logic
- JavaScript and Python code steps with npm packages
- Multi-step AI agents with human approval
- Over 1,500 integrations plus reusable templates
- Connects to OpenAI, Anthropic, Google or local models
- Role-based access and audit trails
- Self-hosting with Docker or managed cloud
Pricing: Free self-hosted Community Edition. Hosted plans cost 20€ (Starter), 50€ (Pro) and 667€ (Business) per month billed annually, scaled by workflow executions; Enterprise is custom. Free trial available.
#4
An LLM application platform for building AI workflows, RAG pipelines and agents on one canvas, deployable in the cloud, a private VPC or self-hosted.
- GitHub stars
- 161k
- Last commit
- today
- Latest release
- 1.19.0
- Self-hosted
- Yes
- Hosted version
- Available
dify.ai
Dify is a platform for building applications on top of large language models. Instead of wiring together prompts, retrieval code and model APIs by hand, teams assemble AI workflows, knowledge pipelines and agents in a shared visual workspace, then move them from prototype to production without changing stacks.
The product covers a workflow studio for agentic flows, a knowledge pipeline that prepares searchable knowledge bases for retrieval-augmented generation, model management across many providers, and a marketplace of tools, models and integrations. Observability integrations such as Opik, Langfuse and Arize Phoenix help trace and debug runs once an app is live.
Dify comes in a few editions: a community edition you deploy yourself with Docker, a hosted cloud service, and an enterprise edition for private deployments. The repository carries a custom license rather than a standard one, so check its terms before offering Dify as a service to others.
Key features
- Visual workflow studio for agentic apps
- Knowledge pipelines for retrieval-augmented generation
- Model management across many LLM providers
- Marketplace of tools, models and integrations
- Observability integrations such as Langfuse
- Deploy on cloud, VPC or Docker
Pricing: Free Sandbox on Dify Cloud and a free self-hosted Community edition. Cloud Professional costs $590 and Team $1590 per workspace per year; Enterprise is custom.
#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 LLM engineering platform for tracing, evaluating and improving AI applications, with prompt management, datasets and a playground, self-hosted or cloud.
- GitHub stars
- 37k
- Last commit
- today
- Latest release
- v4.79.0
- Self-hosted
- Yes
- Hosted version
- Available
langfuse.com
Langfuse is an open-source LLM engineering platform that helps teams develop, monitor, evaluate and debug AI applications together. You instrument your app, and Langfuse records traces of LLM calls and surrounding logic such as retrieval, embeddings and agent actions, so complex runs and user sessions can be inspected and debugged.
Prompt management lets you centrally version and iterate on prompts, with caching on server and client so that changes do not add latency to your app. Evaluation features cover LLM-as-a-judge, code evaluators, user feedback, manual labeling and custom pipelines through the API and SDKs. Datasets provide test sets and benchmarks, there is an LLM playground for trying prompts, and integrations exist for OpenAI, LangChain and LlamaIndex. It is built on the ClickHouse database, and the Langfuse team has been part of ClickHouse since January 2026.
You can use Langfuse Cloud or self-host it, which the maintainers say takes minutes. The repository license is listed as 'Other' because it combines open-source and enterprise components, so check the terms. It suits teams shipping production LLM features who need visibility into quality, latency and cost.
Key features
- Tracing of LLM calls, retrieval and agent actions
- Prompt versioning with caching
- LLM-as-a-judge and custom evaluations
- Datasets for tests and benchmarks
- Interactive LLM playground
- Integrations with OpenAI, LangChain and LlamaIndex
Pricing: Core has a $29 monthly base that includes 100k units, then $8 per 100k units with volume discounts. Hobby and Pro tiers exist but their prices are not shown in the text; Enterprise is by sales.
#7
A visual platform for building and deploying AI agents and workflows, with Python-customizable components and built-in API and MCP server support.
- GitHub stars
- 157k
- Last commit
- yesterday
- Latest release
- v1.13.2
- Licence
- MIT
- Self-hosted
- Yes
langflow.org
Langflow is an open-source platform for building AI-powered agents and workflows. Developers assemble flows in a visual authoring interface and can then deploy each flow as an API or export it as JSON for use in Python applications. It is written in Python and released under the MIT license.
The visual builder is paired with source-code access, so any component can be customized in Python, and an interactive playground lets you test and refine flows step by step. Langflow can orchestrate several agents with conversation handling and retrieval, works with the major LLMs and vector databases, and can expose flows as an MCP server so they become tools for MCP clients. Observability integrations include LangSmith and LangFuse.
You can install the Python package locally with uv, after which it serves the app at a local address, or use Langflow Desktop for Windows and macOS, which bundles its dependencies. It suits developers and AI teams prototyping retrieval and agent workflows who want both a drag-and-drop canvas and the freedom to write code.
Key features
- Visual builder for agents and workflows
- Python source access to customize components
- Interactive playground for testing flows
- Multi-agent orchestration with retrieval
- Deploy flows as APIs or export as JSON
- MCP server mode exposing flows as tools
- Observability integrations such as LangFuse
Pricing: Free and open source under the MIT license.
#8
LlamaParse is a document processing platform that converts PDFs, scans, and Office files to markdown or JSON, and extracts structured data.
- GitHub stars
- 53k
- Last commit
- 2 days ago
- Latest release
- v0.14.25
- Licence
- MIT
- Hosted version
- Available
developers.llamaindex.ai
LlamaParse is a document processing platform from LlamaIndex. It provides APIs to parse PDFs, scans, and Office files into markdown or JSON, and to extract structured data in a user-defined schema. The platform also includes features for classifying, segmenting, and indexing documents.
It offers SDKs for Python, TypeScript, Go, and Java, and can be accessed via a single API key. The platform includes a web UI for extraction and supports batch processing, polling, and latency management for production use.
Key features
- Parse converts PDFs, scans, and Office files to markdown or JSON
- Extract returns JSON in a user-defined schema
- Classify, Split, and Index cover sorting, segmenting, and retrieval
- SDKs for Python, TypeScript, Go, and Java
- Web UI for extraction
- Supports batch processing, polling, and latency management
#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
MLflow is an open-source platform for debugging, evaluating and monitoring AI agents, LLM applications and machine learning models.
- GitHub stars
- 29k
- Last commit
- yesterday
- Latest release
- v3.18.0
- Licence
- Apache-2.0
- Self-hosted
- Yes
- Hosted version
- Available
mlflow.org
MLflow is an open-source AI engineering platform for agents, LLM applications and ML models. It helps teams debug, evaluate, monitor and optimize AI applications in production while keeping control of costs and access to models and data. It is written in Python, released under the Apache-2.0 license, and has been developed since 2018, with topics covering MLOps, model management and LLMOps.
For LLM and agent work it offers production observability with traces, plus evaluation, prompt management and prompt optimization, and an AI Gateway that governs costs and model access. It works with Python, TypeScript and JavaScript, Java and other languages, and integrates with OpenTelemetry and MCP. Getting started means starting an MLflow server, enabling logging in your code and running it, then exploring traces and metrics in the web UI on port 5000. A setup wizard can connect to an MLflow server or a Databricks workspace and add tracing with a coding agent.
Key features
- Tracing and observability for LLM apps and agents
- Evaluation tools for models and agents
- Prompt management and prompt optimization
- AI Gateway for cost and model access control
- OpenTelemetry and MCP integration
- Web UI for exploring traces and metrics
Pricing: Free and open source under the Apache-2.0 license; the README also mentions connecting to a Databricks workspace.
2 more Azure AI Foundry alternatives
Azure AI Foundry alternatives: questions
- What is the best open-source alternative to Azure AI Foundry?
- Ollama is the top-ranked open-source alternative to Azure AI Foundry 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, n8n, Dify and LiteLLM.
- What are the best commercial alternatives to Azure AI Foundry?
- Google Vertex AI, IBM watsonx, Amazon SageMaker, OpenAI API Platform and Amazon Bedrock are among the hosted, closed-source alternatives to Azure AI Foundry listed on Enlisted, which lists 14 in total. Compare their pricing and features on each tool page.
- Are these Azure AI Foundry alternatives free?
- All 12 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. 8 also offer a paid or managed cloud version if you'd rather not host it yourself.
- How is this list of Azure AI Foundry alternatives ranked?
- By a score built from GitHub stars, star growth over the last 30 days and how recently the code changed. 11 of these projects shipped code in the last 30 days. Data is refreshed daily, and nobody can pay to move up.