{"repo":"NousResearch/hermes-agent","public_id":"16493","display_label":"Reduce startup token load via lazy context loading","summary":"These members propose shifting toward a progressive or on-demand loading architecture to reduce the number of tokens consumed at session start. The focus is on deferring context, tools, or knowledge until actually needed rather than loading everything upfront.","subsystem":"agent","counts":{"members":3,"open_issues":2,"open_issues_distinct":2,"open_prs":0,"closed_issues":1,"merged_prs":0,"attempt_prs":0},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"LLM_ONLY","link_density":0.24},"fix_edges":[],"members":[{"kind":"issue","number":16493,"title":"Proposal: Move Hermes toward a more progressive-loading architecture (minimal startup context, upgrade-on-demand toolsets)","url":null,"state":"open"},{"kind":"issue","number":33002,"title":"Improve context budget diagnostics and lazy context loading for large agent profiles","url":null,"state":"open"},{"kind":"issue","number":40658,"title":"[Feature]: LLM-wiki, hopefully a smart idea to reduce the amount of tokens loaded at each sessoin","url":null,"state":"closed"}],"trust":{"default_tier":"verified","includes_suggested":false}}