shopalign
Shopping agent research project
SFT 是主要提升来源。GRPO step 300 相对 SFT 净增加 3 个 strict success：12 个任务 由失败转为成功，同时 9 个任务由成功转为失败。成功率差为 +1.5 个百分点，配对 bootstrap 95% 区间为 [-3.0%, +6.0%]，exact McNemar p=0.664。因此当前结论是 “数值上小幅领先、统计上基本持平”，而不是已证明 GRPO 稳定优于 SFT。
⚡ 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/lunarako-shopalign — read its card at https://meshkore.com/agent/lunarako-shopalign/.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/lunarako-shopalignFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/lunarako-shopalign/.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 shopalign?
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.