memfor
GitHub
Display
Theme
Motion
memfor
Theme
Motion 
git clone https://github.com/r5rana/agentware.git
cd agentware
git checkout 3c25cdd
claude "hi"
git clone https://github.com/r5rana/agentware.git
cd agentware
git checkout 3c25cdd
codex "hi"

This installs agentware, the open-source engine behind memfor. No tagged release yet. These commands pin commit 3c25cdd.

Apache-2.0. No memfor account. Needs macOS or Linux (Windows via WSL), git, Python 3, bash, jq, and Claude Code or Codex.

Send setup steps to my computer Join the Teams waitlist

Run 42d58a0 LongMemEval-S, recorded 25 June 2026, 15:34:44 UTC.

  • clean tree
  • determinism ok
  • cited on this site
Reproduce this number

Reproduce at commit 42d58a0, which recorded this row. The site's install commands pin a later commit that hasn't been re-run yet.

Benchmark metrics
Metric Value Definition
Recall@5 0.9140 Mean over questions of |evidence ∩ top-k| / |evidence|.
nDCG@5 0.8831 With binary relevance.
MRR 0.9104 Mean of 1/rank of the first evidence session.
Precision@5 0.3328 Mean over questions of |evidence ∩ top-k| / k. It can't reach 1 when a question has fewer than k evidence sessions, so it is shown on receipts only.
Conditions
Queries 470
k 5
Strategy bm25
Gold path benchmarks/longmemeval/longmemeval_s_cleaned.json
Tests ran 332
Tests failed 0
Environment Hardware, OS and Python version: not recorded for this run.
Ledger row 86
Raw row 
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "42d58a0", "committed": "2026-06-25T15:34:24Z", "dirty": false, "gold_path": "benchmarks/longmemeval/longmemeval_s_cleaned.json", "metrics": {"latency_ms_mean": 10.522725419116583, "latency_ms_p50": 10.51206249394454, "mrr": 0.9103777978731046, "ndcg_at_k": 0.8830615827171846, "precision_at_k": 0.33276595744680854, "recall_at_k": 0.9140425531914894}, "mode": "eval", "num_queries": 470, "reliability": 96.56, "run": "2026-06-25T15:34:44Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmark): LongMemEval scorer + Mode A baseline + public repro docs", "suite": "longmemeval", "top_k": 5}
reliability is an internal composite health score (0–100), not a benchmark metric.
Esc