docs: refresh agent memory evaluation

[yvette-carlisle]

Summary

• add a machine-readable research run for the June 2026 agentmemory/dreaming selection decision
• refresh the external memory project inventory and comparison docs with agentmemory plus OpenAI/Anthropic/Google dreaming evidence
• add research routing docs and update README/governance links for docs/research run files

Decision

Continue ELF as the evidence-bound memory core. Do not replace it with agentmemory or managed dreaming. Treat agentmemory and managed dreaming systems as baselines/adapters while prioritizing reviewable derived consolidation, viewer/observability, and graph-lite/knowledge-memory work.

Verification

• python3 /Users/x/.codex/plugins/cache/hack-ink/research/0.1.0/scripts/validate_research_run.py --run-file docs/research/2026-06-08-agent-memory-selection.json
• python3 /Users/x/.codex/plugins/cache/hack-ink/research/0.1.0/scripts/run_research.py --run-file docs/research/2026-06-08-agent-memory-selection.json
• python3 /Users/x/.codex/plugins/cache/hack-ink/playbook/0.3.0/scripts/semantic_drift_audit.py --rev HEAD
• git diff --check
• cargo make checks