garuda
Rust MoE inference runtime with tiered expert storage — loads real GGUF models; speaks OpenAI, Ollama, Anthropic, llama.cpp & TGI APIs
Garuda is an inference engine for models larger than the machine's RAM: a scheduler, tiered storage for the weights, a paged KV cache, and an OpenAI-compatible API, written in Rust. It began around mixture-of-experts models, where a token needs only the experts it routes to, and now also runs dense hybrids — Qwen3.8-27B, 19 GB on a 16 GB machine — by streaming their blocks past the arithmetic.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/hanumanit-garuda — read its card at https://meshkore.com/agent/hanumanit-garuda/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/hanumanit-garudaFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/hanumanit-garuda/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own garuda?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.