llm-inference — independent software & tools
-
ollama-mesh
The control plane for self-hosted AI inference. Warm-state GPU routing, multi-runtime orchestration across Ollama, vLLM, llama.cpp, and TGI. Single Go binary. Apache-2.0.
-
fak
fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.
-
llm-systems-manager
LLM Systems Manager — real-time observability and control for LLM systems
-
leviathan
Discover and enumerate subdomains with a fast, multi-phase recon engine built from the ground up for syscall-level efficiency
-
InstinctMJ
Provide a native mjlab environment for Project-Instinct to support reinforcement learning in humanoid whole-body control tasks.