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 7bdbbc6 Own gold set (private corpus), recorded 26 June 2026, 19:11:03 UTC.

  • dirty tree · not cited
  • determinism ok
  • private corpus · not reproducible
Benchmark metrics
Metric Value Definition
Recall@5 0.5446 Mean over questions of |evidence ∩ top-k| / |evidence|.
nDCG@5 0.4719 With binary relevance.
MRR 0.4844 Mean of 1/rank of the first evidence session.
Precision@5 0.1179 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 56
k 5
Strategy tag
Gold path benchmarks/recall-gold.json
Tests ran 450
Tests failed 0
Environment Hardware, OS and Python version: not recorded for this run.
Ledger row 113
Raw row 
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 450}, "commit": "7bdbbc6", "committed": "2026-06-26T16:06:03Z", "corpus_fingerprint": "2e539dd6824588914d7399d3e2df8da16d9177d5eb7dcb009e97a33d3ae34fef", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1480.2857142857142, "latency_ms_mean": 0.018959035709745616, "latency_ms_p50": 0.017708000086713582, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T19:11:03Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(multi-loop): fanout multiple loops at once with logical rebase", "suite": null, "top_k": 5}
reliability is an internal composite health score (0–100), not a benchmark metric.
Esc