AJEAN
A single self-compiling binary that runs an AI assistant at home, with chat, persistent memory, tool use, and end-to-end encrypted remote access, on top of a self-built llama.cpp.
AJEAN provides everything around a locally run language model in one binary: a chat interface, an OpenAI-compatible API endpoint, tool use, service management, and hardware management. The inference engine is llama.cpp, which AJEAN compiles itself for the machine it runs on, so there is no separate runtime dependency, CMake flag, or container to manage.
The chat interface includes visible reasoning, persistent memory, automatic context compaction as a conversation grows, multiple saved sessions, and an editable system prompt. A single command turns on the model's tools on the host machine: running terminal commands, writing and editing files by exact replacement, analyzing attached or screenshotted images, keeping persistent Markdown memory across sessions, searching and reading web pages, driving a browser, and calling the tools of configured MCP servers.
It runs on Linux, macOS, and Windows, with documentation in French and English, and supports encryption at rest and end-to-end encrypted remote access.