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 5b9e4b4 Own gold set (private corpus), recorded 24 June 2026, 22:15:00 UTC.

  • dirty tree · not cited
  • determinism ok
  • private corpus · not reproducible
Benchmark metrics
Metric Value Definition
Recall@5 0.9821 Mean over questions of |evidence ∩ top-k| / |evidence|.
nDCG@5 0.9440 With binary relevance.
MRR 0.9440 Mean of 1/rank of the first evidence session.
Precision@5 0.2179 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 bm25
Gold path benchmarks/recall-gold.json
Tests ran 50
Tests failed 0
Environment Hardware, OS and Python version: not recorded for this run.
Ledger row 2
Raw row 
{"ablation": {"baseline": "tag", "delta": {"context_tokens_mean": 2655.0714285714284, "latency_ms_mean": 2.2753645909168494, "latency_ms_p50": 2.264604496303946, "mrr": 0.3687499999999999, "ndcg_at_k": 0.36858670534433735, "precision_at_k": 0.0785714285714286, "recall_at_k": 0.3303571428571428}, "treatment": "bm25"}, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 50}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3773.035714285714, "latency_ms_mean": 2.2810275534409032, "latency_ms_p50": 2.2696249943692237, "mrr": 0.944047619047619, "ndcg_at_k": 0.9440244501430693, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "ablate", "num_queries": 56, "reliability": 99.29, "run": "2026-06-24T22:15:00Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
reliability is an internal composite health score (0–100), not a benchmark metric.
Esc