As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their specific needs, as well as to inspect any part of the training process.




The best open source alternative to OpenClaw is Apertus. If that doesn't suit you, our users have ranked more than 100 alternatives to OpenClaw and many of them is open source so hopefully you can find a suitable replacement. Other interesting open source alternatives to OpenClaw are NanoClaw, Goose OSS, Thunderbolt and Maid (AI).
As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their specific needs, as well as to inspect any part of the training process.




Lightweight AI assistant runs in Apple containers with isolated Linux container processes for superior OS-level security, transparency, and privacy compared to complex chatbots, enabling quick code review, easy customization, and minimal dependencies for all users.




An open-source platform for seamless automation in engineering tasks, providing local execution and control. Customizable with any LLM for enhanced autonomy, enabling developers to efficiently handle debugging to deployment tasks while preserving privacy.



Open-source AI platform for deploying language models across desktop and mobile systems, features model selection, on-premises setup, enterprise-level encryption, advanced security auditing, and flexibility for organizations seeking total data ownership and compliance.

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.




MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research.


Ask questions to your documents without an internet connection, using the power of LLMs. 100% private, no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!

Empowering LLM researchers and hobbyists with seamless control over self-hosted models. Connect remotely, customize prompts, manage chats, and fine-tune configurations. All in one intuitive app.




Complete LLM chatbot implementation, offering tokenization, pretraining, finetuning, evaluation, inference, and a simple web UI. Runs on a single 8xH100 node, features a hackable codebase, dependency-lite design, and automates the full workflow via scripts.

An Extensible Multi-person interactive Agent Framework Powered by LLM Code Generation; Support: QQ, Discord, Minecraft, Bilibili Live, SSE(SDK) ...




Drop-In OpenAI replacement, On-device, local-first, Generate text/image/speech/music/etc... Backend Agnostic: (llama.cpp, diffusers, bark.cpp, etc...), Optional Distributed Inference(P2P/Federated).



