Everything in the orbit of claude-codex-local — the upstream project, supported runtimes, routing backends, model hubs, and the harnesses we bridge to.
Get up and running with LLMs locally. Primary backend for claude-codex-local.
Inference of LLaMA models in pure C/C++. High-performance GGUF support.
High-throughput, memory-efficient inference engine for LLMs.
Hardware-aware model selection. Analyzes your system; recommends models that fit.
Local cloud-routing proxy for alternative providers (OpenAI, DeepSeek, ...).
Hosted SaaS alternative to 9router. Unified API for dozens of LLM providers.