Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Home / Open Source Radar / Chat & Self-hosted / anything-llm

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Stars68.4k
Forks7.7k
LanguageJavaScript
LicenseMIT

About this project

anything-llm is an open-source chat and self-hosting project on GitHub: Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience. It belongs to the chat and self-hosting part of the ecosystem: a conversational front end you run on hardware you control. It is maintained by Mintplex-Labs and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged agent-computer, agent-harness, agent-orchestration, agentic-ai, agentic-workflow, ai-agents, computer-use, hermes-agent, llm, local-ai, localai and multimodal, which is a fair summary of what it covers. The practical payoff is ownership. Prompts, conversation history and model choice stay on your own infrastructure, and nothing has to be sent to a third-party service unless you configure it.

It is written mainly in JavaScript and released under MIT, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 17, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 68,363 stars; 7,723 forks; primary language JavaScript; license MIT; last commit on November 17, 2026; topics agent-computer, agent-harness, agent-orchestration, agentic-ai, agentic-workflow, ai-agents.