17 open-source alternatives ranked by real activity

Open-source Claude alternatives

A curated, ranked list of the 17 best open-source alternatives to Claude.

The best open-source alternative to Claude is Ollama. If that doesn't suit you, other good options are Open WebUI, Omnara, oh-my-claudecode and Jan.

Commercial alternatives to Claude include Grok, Meta AI, Microsoft Copilot and ChatGPT. See all 46.

Claude alternatives are mainly AI tools, but some are also AI infrastructure tools. 13 of them shipped code in the last 30 days, 17 can be self-hosted, and 13 use a permissive licence.

Last updated November 13, 2026 · ranked by GitHub stars, growth and recent commits

Ollama

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.comOllama homepage screenshot

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.

Open WebUI

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.comOpen WebUI homepage screenshot

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.

Omnara

Omnara is an open-source, self-hostable platform that provides a single API to deploy and run AI agents for users and teams on any model and machine.

GitHub stars
3.4k
Last commit
today
Latest release
omnarad-v0.2.21
Licence
Apache-2.0
Self-hosted
Yes
omnara.comOmnara homepage screenshot

Omnara is an open-source managed agent platform that serves as a self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. It provides a single API to deploy and run agents for users and teams, on any model, any machine, and any cloud.

The platform is designed to be hosted anywhere, allowing users to own their data. It supports deployment via CLI, TypeScript SDK, and cURL, and can be used to build agents in product dashboards, internal Slack agents, specialized workflows like code review, and interactive CLI experiences.

Key features

  • One API to deploy and run agents on any model and machine
  • Self-hostable and open-source
  • Deploy agents with a single prompt
  • Supports CLI, TypeScript SDK, and cURL
  • Agents can be integrated into product dashboards, Slack, and CLI
  • Examples include SRE, coding, signal digest, browser, and video generation agents

oh-my-claudecode

oh-my-claudecode is a plugin that lets Claude Code coordinate Claude, Gemini and Codex workers through agents, skills and tools.

GitHub stars
41k
Last commit
today
Latest release
v5.8.4
Licence
MIT
oh-my-claudecode.devoh-my-claudecode homepage screenshot

oh-my-claudecode is a multi-AI orchestration plugin for Claude Code. It coordinates Claude, Gemini and Codex using 19 specialised agents, 48 skills and 50 MCP-powered tools, according to its homepage. The version shown is 5.7.9, with release notes covering remote approval gates for a graph workflow, new skills and HUD fixes.

Gemini and Codex workers are real CLI processes started in tmux panes, while Claude decomposes tasks and combines the results. Several execution modes are listed, including Autopilot for fully autonomous runs, Ralph for looping until completion, and Deep Interview for clarifying requests. It installs from the Claude Code plugin marketplace or as an npm package.

Key features

  • Orchestrates Claude, Gemini and Codex
  • Parallel CLI workers in tmux panes
  • Autopilot mode for autonomous runs
  • Claude splits and recombines tasks
  • Install through plugin marketplace or npm

Jan

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.aiJan homepage screenshot

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.

OpenWork

A free, open-source desktop app where AI agents work on your files, built on OpenCode, compatible with 50+ model providers and shareable skills and MCP servers.

GitHub stars
24k
Last commit
today
Latest release
v0.18.66
Self-hosted
Yes
openworklabs.comOpenWork homepage screenshot

OpenWork is a free, open-source desktop application, available on macOS, Windows and Linux, in which AI agents work on your own files. It is presented as an alternative to Claude Cowork and Codex and is built on OpenCode. It is model-agnostic: connect more than fifty providers with your own API keys, or run local models through Ollama, and no OpenWork account is needed to use it locally.

A key idea is sharing: teams can distribute skills and MCP servers, and attaching one OpenWork MCP server to Codex, Claude Code, Cursor or a similar agent lets you carry the same skills, MCPs and connected services across tools, teammates and machines. The desktop app gives you a dedicated workspace but is optional, because the capabilities work from whichever agent you already use. For bigger organizations an admin interface lets administrators release capabilities, control who can use them and set up either shared or per-user connections.

The desktop app is MIT licensed according to the README, while the repository license is listed as 'Other' on GitHub, so confirm what applies to each component. It suits individuals and teams who want agentic automation of file-based work with control over models and data.

Key features

  • Desktop app for macOS, Windows and Linux
  • Agents working on your local files
  • Any model: 50+ providers or local via Ollama
  • Shareable skills and MCP servers
  • Single MCP to reuse skills across other agents
  • Admin interface for access and connections

Pricing: The first 5 cloud seats are free and self-hosting is free for up to 5 users. Team costs $10 per seat per month; Enterprise is custom, and self-hosting is free to evaluate for 30 days at any size.

Suna

Kortix (the suna repository) is an open-source platform for running AI agents on cloud sandboxes, with agents, skills, memory and connectors kept in one git repo.

GitHub stars
21k
Last commit
yesterday
Latest release
v0.15.9
Self-hosted
Yes
Hosted version
Available

Kortix describes itself as an open-source AI operating system. The agents, the skills they share, the company memory and every connector live in a single git repository that is versioned and shared. Agents work on real cloud computers, each session in an isolated sandbox on its own branch, and their output reaches the team as a change request that a human approves.

It is model-agnostic: any provider, using your own API keys. You can run it on your own infrastructure, inside your VPC, or use the managed cloud. Listed uses include agents in Slack or Microsoft Teams, background coding agents, scheduled or webhook-triggered automations, approval-gated AI employees and governed agents with per-tool rules, an audit trail and SAML SSO.

Setup is through a CLI: install it, run kortix init to scaffold a project, then kortix ship to bring it live in the cloud. Sessions are started from the command line, and kortix cr ls lists what an agent has proposed. The project is explicit about fit: it is not aimed at fixed visual flowcharts or a plain chat window over documents.

Key features

  • Agents, skills, memory and connectors stored in one git repo
  • Isolated cloud sandbox per session on its own branch
  • Human-approved change requests for agent output
  • Works with any model using your own API keys
  • Agents reply inside Slack or Microsoft Teams threads
  • Scheduled or webhook-triggered agent automations
  • Governance controls including approval gates and SAML SSO

Pricing: Self-hosting is listed as free; the managed cloud is listed as from $20/mo in credits, with unlimited members.

Eigent

Eigent is an open source desktop application that lets users work alongside AI agents to automate tasks across the web and desktop.

GitHub stars
16k
Last commit
yesterday
Latest release
v1.0.7
Licence
Apache-2.0
Self-hosted
Yes
eigent.aiEigent homepage screenshot

Eigent is an open source desktop application that provides a multi-agent workforce. It connects to the user's context and can control the browser and desktop apps to automate real work. The application is model agnostic, allowing users to choose the AI model that powers the agents.

It is designed for users who want to automate tasks such as market research, competitor analysis, and content drafting. The interface includes a workspace with files, automations, and sessions, and agents can use skills and MCP tools to execute tasks. It is positioned as a local and free alternative to Claude Cowork and Codex.

Key features

  • Open source
  • Model agnostic
  • Fully customisable
  • Can control browser and desktop apps
  • Multi-agent workforce
  • Includes skills and MCP tools

Hugging Face Chat UI

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.coHugging Face Chat UI homepage screenshot

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.

AgentConnect

AgentConnect is an open-source multi-agent platform that lets teams mention agents in chat to automate tasks.

GitHub stars
1.5k
Last commit
yesterday
Latest release
v2.13.0
Licence
Apache-2.0
agentconnect.mdAgentConnect homepage screenshot

AgentConnect is an open-source multi-agent platform described as an alternative to Claude Tag. It allows users to mention any agent in a chat-like interface wherever work happens, and agents work alongside the team and each other, learning as they go.

The platform provides a console to operate the entire fleet of agents, including agent management, sessions, schedules, tools and skills, knowledge, and daemons. It is suited for teams that want to deploy and coordinate multiple autonomous agents to handle tasks such as support, payment operations, code review, and onboarding.

Key features

  • Mention agents with @ to trigger actions in chat
  • Console for managing agents, sessions, schedules, tools, knowledge, and daemons
  • Agents can work together and learn from interactions
  • Tools and skills connectors (e.g., Figma, Fireflies, web-search, code-review, summarize)
  • Knowledge management with read-only access at session start and suggested entries for review
  • Daemon health monitoring and schedule management for recurring tasks

7 more Claude alternatives

Commercial Claude alternatives

Hosted, closed-source products that compete with Claude. Showing 12 of 46.

See every Claude alternative on its tool page

Claude alternatives: questions

What is the best open-source alternative to Claude?
Ollama is the top-ranked open-source alternative to Claude 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 Open WebUI, Omnara, oh-my-claudecode and Jan.
What are the best commercial alternatives to Claude?
Grok, Meta AI, Microsoft Copilot, ChatGPT and Perplexity are among the hosted, closed-source alternatives to Claude listed on Enlisted, which lists 46 in total. Compare their pricing and features on each tool page.
Are these Claude 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. 3 also offer a paid or managed cloud version if you'd rather not host it yourself.
How is this list of Claude alternatives ranked?
By a score built from GitHub stars, star growth over the last 30 days and how recently the code changed. 13 of these projects shipped code in the last 30 days. Data is refreshed daily, and nobody can pay to move up.

People also look for alternatives to…

View all