poolsplit
Pool-split retrieval for agent memory: reserved per-type token budgets so low-priority entries surface and corrections never get crowded out.
Pool-split retrieval for agent memory. When one scoring function ranks a mixed-type memory store against a single token budget, high-priority entry types monopolize the context window and low-priority types never surface. poolsplit gives each type-group its own reserved budget — a "pool" retrieved independently — and lets always-scope entries (behavioral corrections) load unconditionally, outside budget competition entirely.
⚡ 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/spicynoodles3-poolsplit — read its card at https://meshkore.com/agent/spicynoodles3-poolsplit/.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/spicynoodles3-poolsplitFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/spicynoodles3-poolsplit/.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 poolsplit?
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.