π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Darwin capability evolution β plan
Branch: darwin/capability-evolution-2026-06-26
Started: 2026-06-26
Goal
Drive ruflo capabilities toward SOTA across the dimensions we already
benchmark, using a /loop 5m autonomous loop. Each tick spawns one
claude -p (headless, Read/Edit/Bash only, --max-budget-usd capped) to
do a single optimization cycle, so this conversation stays focused on
orchestration and the per-tick spend is bounded.
Per-tick contract
A single tick = one claude -p invocation that does end-to-end:
- Read
docs/darwin/log.jsonlβ last N entries, find current champion scores per dimension. - Pick the worst-relative-to-SOTA dimension. SOTA baselines: BEIR NFCorpus β nDCG@10 β₯ 0.36 (state-of-the-art hybrid) BEIR ArguAna β nDCG@10 β₯ 0.55 BEIR SciFact β nDCG@10 β₯ 0.74 BEIR TREC-COVID β nDCG@10 β₯ 0.78 GAIA L1 β exact-match β₯ 0.62 (LangGraph reference) ADR coverage β adr-index storage success β₯ 0.99
- Propose ONE targeted change (parameter tune, prompt rewrite, dep bump, algorithm swap). Keep it small enough that a benchmark subset can score it in β€4 minutes.
- Apply, run the relevant benchmark/audit:
BEIR β
node scripts/bench-beir.mjs <dataset> --top-k 10ADR βnode plugins/ruflo-adr/scripts/import.mjs --dry-runOIA βnpx ruflo metaharness oia-audit --format json - Compare delta to prior champion for that dimension: Ξ > 0 β commit, update champion, log success Ξ β€ 0 β revert, log noImprovement benchmark error β revert, log error
- Append one JSONL line to
docs/darwin/log.jsonlwith: { iter, ts, dimension, change, deltaScore, action, commit }
Termination
- 3 consecutive iterations without Ξ > 0 across any dimension β stop
- Or explicit user stop
Spend cap per tick
claude -p --max-budget-usd 0.50 --model haiku for routine ticks.
Escalate to sonnet only when haiku reports "task too complex" 3x in
a row.
SOTA-proof
A dimension is "proven SOTA" when:
- It exceeds the baseline above by β₯1%
- The benchmark run is reproducible (3 consecutive runs within 1Ο)
- The git commit is signed and witnessed