consciousness/poc-memory
ProofOfConcept e9791991a7 scoring: rebalance consolidation plan using Elo ratings
After health metrics compute the total agent budget, read
agent-elo.json and redistribute proportionally to Elo ratings.
Higher-rated agent types get more runs.

Health determines HOW MUCH work. Elo determines WHAT KIND.

Every type gets at least 1 run. If no Elo file exists, falls back
to the existing hardcoded allocation.

Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
2026-03-14 20:03:18 -04:00
..
.claude feedback: not-relevant/not-useful commands, edge strength adjustment 2026-03-14 12:14:17 -04:00
agents agent evaluate: sort agent actions by quality using Vec::sort_by with LLM 2026-03-14 19:24:07 -04:00
defaults split into workspace: poc-memory and poc-daemon subcrates 2026-03-08 20:43:59 -04:00
schema provenance: convert from enum to freeform string 2026-03-11 01:19:52 -04:00
src scoring: rebalance consolidation plan using Elo ratings 2026-03-14 20:03:18 -04:00
build.rs split into workspace: poc-memory and poc-daemon subcrates 2026-03-08 20:43:59 -04:00
Cargo.toml evaluate: switch to Elo ratings with skillratings crate 2026-03-14 19:53:46 -04:00
config.example.jsonl split into workspace: poc-memory and poc-daemon subcrates 2026-03-08 20:43:59 -04:00