English · Français
Derived project, personal use. This repository is a fork of nathaninline/ajean, created and maintained by nathaninline — the upstream project, and the only source of published AJEAN releases. Everything below describes AJEAN in general. This fork carries a private patch line (0.18.16.2 Cresius, built on upstream
v0.18.16) for one specific machine: the Strata MoE engine on AMD (context size, KV quantization, VRAM reserve, AMD vision), EmbeddingGemma 2 semantic memory, the Ajean↔Ajean bridge (two Ajean instances on one local network talking to each other, each keeping its own brain), call de-duplication and a tunable compaction threshold. Those additions are not upstream releases, are not tested elsewhere, and are not guaranteed to work anywhere else. To install AJEAN, use the releases published on nathaninline/ajean. The MoE engine used here comes from Niko1221/Strata. What exactly this repository changes: NOTICE.md.
Run your own AI at home. AJEAN is a single program that turns a computer with a graphics card (or a plain CPU) into a complete AI assistant: a chat interface, memory, tools, web access, scheduled tasks, and access from your phone, with nothing leaving your machine.
AJEAN handles everything around the model. The model itself runs on llama.cpp, which AJEAN installs and keeps up to date for you.
- One file, no dependencies. No Docker, no Python, no runtime to install. Linux, Windows and macOS.
- An assistant, not just a model. It remembers, organizes work into projects, runs commands, reads the web, drives a browser, and works on its own on a schedule.
- Your data stays yours. Everything runs on your machine. Memory and conversations can be encrypted at rest, and remote access is encrypted end to end.
- Use it from anywhere. The same conversations on your computer and your phone, live.
- Plugs into your tools. An OpenAI-compatible endpoint for any third-party app.