| /plans/agent-memory-leaderboard.md |
0.90 |
Plan: Agent Memory Leaderboard entry |
plan, benchmark, leaderboard, agent-memory, agentic-search, adapter, academic-board, coding-agent-memory, gpt-4o-mini, open-source, public-repository, digitalocean, deployment, production, evaluation, live-validation, conformance, load-test, status:active |
| /benchmarks.md |
0.80 |
Benchmarks |
benchmarks, tokens, cost-per-query, retrieval, evaluation, graphifymd, ckg, model-tokens |
| /plans/graph-focus/answer-evaluation.md |
0.80 |
Independent answer evaluation |
graph, evaluation, answer-quality, benchmark, reader, scorer, citations, provenance, usage, process-lifecycle, corpus, held-out, status:active |
| /roadmap/graph-evaluation.md |
0.80 |
Graph evaluation delivery |
graph, benchmark, evaluation, tokens, soul, real-corpus, baseline, roadmap |
| /research/graph-neighborhood-performance.md |
0.75 |
Graph neighborhood performance and token results |
graph, neighborhood, performance, benchmark, tokens, evaluation, pr-review, regression |
| /plans/graph-focus/evaluation.md |
0.75 |
Graph focus evaluation |
graph, benchmark, retrieval, evaluation, relevance, tokens, performance, usability, status:proposed, end-to-end, provider-usage, real-corpus, soul, section-first, reader-policy |
| /research/journal-quality-2026-10-14.md |
0.70 |
Journal entry quality baseline \(2026-10-14\) |
research, benchmark, journal, quality, session-facts, nudge, evaluation, freshness, curation, baseline, replay, pipefail |
| /journal/2026-09-15.md |
0.65 |
2026-09-15 |
journal, graph, evaluation, benchmark, dataset, human-review, completion, baseline |
| /journal/2026-09-16.md |
0.60 |
Demarkus journal: 2026-09-16 |
demarkus, graph, evaluation, confinement, benchmarks |
| /memoryleaderboard/journal/2026-08-17.md |
0.60 |
Journal 2026-08-17 |
journal, memoryleaderboard, phase-5, minimax, minimax-m3, academic-board, gpt-4o-mini, apache-2.0, open-source, deployment, credential-safety, testing, evaluation |