Skip to main content

Modelverse

Modelverse is the CLIKA model library: models packaged so that ClikaRT loads and runs them as they are. It is a catalog of registered model families covering language, vision, audio and multimodal models, the clika-modelverse executable that fetches and runs any of them, and a C++ library when you want the same machinery inside your own application. One command takes a model name to generated text; one more serves it over HTTP.

Why Modelverse​

For the AI developer. The checkpoints you already use are the input. Modelverse resolves a Hugging Face Hub repo id, a pasted Hugging Face URL or a local directory to model files, matches them to a registered family, and runs them; ONNX exports, GGUF quantizations and safetensors checkpoints all load through ClikaRT unchanged. clika-modelverse <model> prompt "..." is a working generation before you have written any code, and every knob you expect (sampling, system prompt, context length, KV cache mode) is a flag.

For the backend engineer. A model becomes an OpenAI-compatible endpoint in one command. clika-modelverse <model> serve hosts /v1/chat/completions with streaming, plus embeddings, transcription and the other engine routes a model family provides, and existing OpenAI clients point at it by changing one base URL. clika-modelverse is built for scripts: stdout carries only the payload, diagnostics go to stderr, and the exit codes follow a fixed four-value contract. No Python runs anywhere.

For the embedded developer. A model family ships quantized variants, and you pick the one that fits the device. A GGUF repo with ten quantizations is a selector away (<org>/<repo>:Q6_K), the option table with file sizes prints before anything downloads, and the same model runs wherever ClikaRT runs, from a workstation GPU to a phone.

For the defense, healthcare and finance developer. Nothing here requires a network at run time. Fetch a model on a connected machine, move the directory, and point Modelverse at it; a local directory is a first-class model source, and an offline flag makes any network touch an error instead of a surprise. The install is one archive extracted into one directory, runtime and Modelverse together, and the models arrive the same way.

For the business. Every model in the catalog has a known license: the catalog records who published each family and under what terms. You do not have to vet checkpoints from unknown sources. Models come straight from Hugging Face by repository id, so the models your team already uses work as-is. Quantized variants run the same model on cheaper hardware, which lowers serving cost. And you do not have to build inference for the popular models yourself. Modelverse already runs them.

What you get​

  • The catalog. Dozens of registered model families, from Llama, Qwen and Gemma through Whisper, CLIP, DETR and Depth Anything. Each family declares its input and output modalities, the checkpoint formats it matches, and the commands it can run. clika-modelverse list prints it.
  • The executable. clika-modelverse inspects (info), downloads (fetch) and runs models. Which commands a model supports (prompt, serve, transcribe, embed, bench and more) depends on its family, discovered per model.
  • The server. An OpenAI-compatible HTTP server with streaming chat completions, a built-in web chat page and a health probe, plus per-modality routes for transcription, embeddings, depth, detection and segmentation.
  • The library. The surface behind all of it, in C++ with Python, C, Kotlin, Go and Rust bindings: fetch a snapshot, load a runnable model, build a serving pipeline, or mount your own engine on the server. For C++, one find_package(Modelverse CONFIG) integrates it; the bindings arrive through their package managers.
  • The packaging. One archive per platform, the ClikaRT runtime and Modelverse inside it, extracted and run in place. A manifest pins the exact runtime each build linked against, so a mismatched pair refuses with a readable error. No installer and no downloads at run time.

Where to go next​