Replace sort-based ranking with proper Elo system: - Each agent TYPE has a persistent Elo rating (agent-elo.json) - Each matchup: pick two random types, grab a recent action from each, LLM compares, update ratings - Ratings persist across daily evaluations — natural recency bias from continuous updates against current opponents - K=32 for fast adaptation to prompt changes Usage: poc-memory agent evaluate --matchups 30 --model haiku Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
47 lines
942 B
TOML
47 lines
942 B
TOML
[package]
|
|
name = "poc-memory"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
|
|
[dependencies]
|
|
capnp = "0.20"
|
|
uuid = { version = "1", features = ["v4"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
bincode = "1"
|
|
regex = "1"
|
|
chrono = "0.4"
|
|
clap = { version = "4", features = ["derive"] }
|
|
libc = "0.2"
|
|
faer = "0.24.0"
|
|
rkyv = { version = "0.7", features = ["validation", "std"] }
|
|
memmap2 = "0.9"
|
|
rayon = "1"
|
|
peg = "0.8"
|
|
paste = "1"
|
|
jobkit = { git = "https://evilpiepirate.org/git/jobkit.git/" }
|
|
jobkit-daemon = { path = "../jobkit-daemon" }
|
|
redb = "2"
|
|
log = "0.4"
|
|
ratatui = "0.29"
|
|
skillratings = "0.28"
|
|
crossterm = { version = "0.28", features = ["event-stream"] }
|
|
|
|
[build-dependencies]
|
|
capnpc = "0.20"
|
|
|
|
[lib]
|
|
name = "poc_memory"
|
|
path = "src/lib.rs"
|
|
|
|
[[bin]]
|
|
name = "poc-memory"
|
|
path = "src/main.rs"
|
|
|
|
[[bin]]
|
|
name = "memory-search"
|
|
path = "src/bin/memory-search.rs"
|
|
|
|
[[bin]]
|
|
name = "poc-hook"
|
|
path = "src/bin/poc-hook.rs"
|