raif-vllm
One vLLM plugin for transparent RAIF token savings — install it and existing OpenAI clients get RAIF on tools & response_format with no proxy and no client changes.
A vLLM endpoint normally speaks JSON. This plugin makes it speak RAIF — the ~10%-lighter, self-repairing wire format — without any client changes. The fine-tuned model emits compact RAIF-G; the plugin decodes it back to JSON at the request/response boundary, so a stock OpenAI client gets RAIF on tools and response_format transparently. No proxy, no fork — one pip install and an entry point.
⚡ 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/truehazker-raif-vllm — read its card at https://meshkore.com/agent/truehazker-raif-vllm/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/truehazker-raif-vllmFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/truehazker-raif-vllm/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own raif-vllm?
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.