Sovereign AI
The complete matrix of local LLMs, image generators, and autonomous agents forged for autonomous infrastructure.
DeepSeek-V3 / R1
Powerful open-source models including V3 (671B) and R1 (Reasoning). Rivals GPT-4o and o1.
Qwen 3 (235B)
Massive 235B param model. The absolute king of coding and mathematics benchmarks in 2026.
Mistral Large 2
Flagship 123B model from Mistral AI. Optimized for multilingual, reasoning, and coding tasks.
DeepSeek V3.1
Refined V3 architecture with improved instruction following and reduced hallucination rates.
Qwen 2.5
Comprehensive LLM series from Alibaba Cloud, excelling in coding, math, and multilingual support.
Google Gemma 3
Gemma 3 (27B) delivers GPT-5 class performance on a single GPU. Optimized for reasoning and agents.
Google Gemma 2
Google's open-weight models (9B, 27B) with class-leading performance and efficient architecture.
Meta Llama 4
The latest generation of Llama. 'Maverick' architecture with 256K context. The new standard for open weights.
Meta Llama 3.1
Meta's flagship open-weight model with 128K context. Supports 8B, 70B, and 405B parameters.
Midjourney
Leading AI image generation tool, known for artistic and photorealistic outputs.
Stable Diffusion 3.5
The latest open-weights image generation model from Stability AI, offering superior prompt adherence.
Mochi-1
High-fidelity open-weights video generation model from Genmo, rivaling closed-source alternatives.
HunyuanVideo 1.5
Tencent's state-of-the-art open-source video generation model with 13B parameters.
FLUX
Next-gen open image generation model from Black Forest Labs. State-of-the-art quality rivaling Midjourney.
GitHub Copilot
AI pair programmer by GitHub/OpenAI. Integrates into VS Code and JetBrains.
Continue
Open-source AI code assistant for VS Code and JetBrains. Use any model (local or API).
TabbyML
Self-hosted AI coding assistant. An open-source, self-hosted alternative to GitHub Copilot.
Atomic Agent
Local-first CLI and TUI coding agent. Runs open-weight models entirely on your machine through a llama.cpp fork, with no account or API key required. Ships 56 built-in tools (browser, filesystem, git, memory, vision), MCP support, and a five-layer local memory system.
Ollama
Get up and running with Llama 3, Mistral, Gemma, and other large language models locally.
Open WebUI
User-friendly WebUI for LLMs (Formerly Ollama WebUI). Supports Ollama and OpenAI-compatible APIs.
Jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
Orkas
Open-source, local-first desktop AI workforce coordinated by a Commander through one chat.