PRO-LONG
Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
PRO-LONG is a minimal memory addition for LLM agents on long-horizon tasks. Our harness appends every observation, action, and outcome verbatim to a single structured log.txt, and the agent retrieves and reasons over it programmatically (grep, Python). We use no subagents or specalized retrieval mechanisms, and use a ~30-line prompt.
⚡ How to use PRO-LONG
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/alexisfox7-pro-longCapabilities
Do you own PRO-LONG?
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.