Everlock 0.10.0
The 0.10.0 release adds two operator tools — an on-demand view of the server's recent log and an explicit restart — makes the git host's address a live setting, names the MCP endpoint at start, and mo
Documentation
Tag: ai
Everlock 0.9.2
The 0.9.2 release restores the embedded model's text recognition and non-English answers, serves IPv4 and IPv6 side by side on every frontend, and repairs `writer` grants on photo instances. Binaries
The embedded model
Every Everlock build embeds **MiniCPM-V 4.6 Thinking**. It is baked into the binary — the same model on every platform, in every container image, with no runtime switch and nothing to download separat
Everlock 0.9.0
The 0.9.0 release makes Everlock a git host: repositories are served over HTTP, browsed in a web UI, and built by CI runs that a push starts. It also replaces the two embedded AI models with one that
One model instead of two — choosing a single vision model
Everlock embeds its language model in the binary. Until now it embedded one of two. The default build carries SmolVLM-256M, small enough to disappear into the executable. A `qwen3` feature swaps it fo
Everlock 0.6.2
The 0.6.2 release brings captions to photo frames and a round of substance fixes: self-update no longer needs three binaries' worth of memory, image previews cache like the immutable content they are,
The gguf-runner inference engine
Everlock runs its AI features on its own inference engine, [**gguf-runner**](https://github.com/apimeister/gguf-runner) — a self-developed, from-scratch GGUF runtime written for this project. It is em
AI backend
The AI backend is Everlock's built-in operator assistant and shared vision runtime. It is exposed in two places: - an interactive prompt mode inside the admin SSH session - image captioning for the im
AI runtime and access model
Everlock embeds a small LLM and exposes it in two places: 1. as a free-text prompt mode inside the admin SSH session (`backend-ai-ssh` + `backend-admin-ssh` + `frontend-ssh`) 2. as an image-caption
Shared AI runtime crate
The embedded LLM that powers the admin SSH prompt mode has been factored out of `backend-ai-ssh` into its own shared crate, `everlock-ai-runtime`. - A new `crates/ai-runtime` crate owns the heavy reso