Compare

What packset measured

packset is the standing-knowledge store in the seat. It writes only on Remember: and Prefer:. The crate explanation holds the rows. Neighbouring systems are named by protocol.

What we measured

LongMemEval_S (doi:10.48550/arXiv.2410.10813), 470 answerable questions, session-level retrieval. The pack writes claims, not harvested chat. Reproduction: scripts/longmemeval_qa.py and docs/orgmode/results/longmemeval-s-qa.org in packset.

Armhit@1recall@5recall@10
packset BM25+0.8550.9140.952
packset fused panel0.8890.9490.981

Answer accuracy on the same 470 uses a local 7 B reader and judge (Qwen2.5-7B-Instruct Q5_K_M, LongMemEval prompts, top five sessions). CombMNZ fusion is 0.549. Lexical alone is 0.532. Labelled sessions, the ceiling for any retriever, are 0.634.

MemoryAgentBench (doi:10.48550/arXiv.2507.05257), same 7 B reader. Conflict-resolution split 0.480. Published retrieval baselines on that split range from 0.155 to 0.295 with a stronger reader. Accurate-retrieval split 0.675 of 2000, against published 0.605 (BM25) and 0.651 (HippoRAG-v2).

Neighbouring published numbers

Two public repositories share the name agentmemory. They report different protocols. The first is session retrieval (R@5). The second is question answering with a hosted generator and a hosted judge. packset publishes both a retrieval row and a local-reader QA row so those protocols stay distinct.

SystemProtocolPublished figureWrite policy
rohitg00/agentmemory LongMemEval-S retrieval, R@5, all-MiniLM-L6-v2 95.2% (their COMPARISON.md) Lifecycle hooks capture transcript text
JordanMcCann/agentmemory LongMemEval QA, hosted generator and judge 96.20% on 481/500 (their README) Chat over a MemoryStore
packset LongMemEval_S session retrieval; QA with a local 7 B reader recall@5 0.949 fused, 0.914 lexical; QA 0.549 against a 0.634 labelled ceiling Remember: and Prefer: only

The 0.949 fused recall@5 is the neighbour of the 95.2% R@5 retrieval figure. The 96.20% QA figure uses a different generator and a different judge. InjecMEM and MINJA describe the risk of writing from a transcript. packset writes only on Remember: and Prefer:. Privacy-of-write.

What the other habitats answer

Retrieval is one store. The seat also cites frozen product, the tracker, this-session claims, argv law, and weighted agreement. Those questions are not retrieval scores.

QuestionStore
What did the human freeze?cards
What does this seat know, standing?packset
What did this unit produce?deedar
What does this node stand on, and who agrees?vissue
What is this session handing out?claimdag
May this argv run?ljos-policyd
Who is right, under trust?ljos-consensus

policyd is argv law

ljos policy -- argv prints the line and any pack rule that matches it. ljos rule writes that law into the pack. ljos-policyd is the TCB when it is on PATH or POLICYD_BIN: it prints allow or deny. Reloading a pack is not a check. ljos-policyd docs · Argv field note.

Source: packset explanation · packset