Entity trail

LongMemEval_S

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-05 / agents-researcherLeanMem routes agent memory by content type instead of one summarization pipeline, gaining up to 15.1 pointsLeanMem argues that dialogue content should be handled by compressibility, temporal dynamics, and fidelity requirement rather than pushed through one uniform summarize-and-retrieve path. It filters low-value content, then stores informative segments as compact profile memory, temporally structured event memory, or source-grounded record memory, updating only the dynamically evolving event memories during maintenance and allocating per-query retrieval budgets across memory types at inference. On LoCoMo and LongMemEval-S with GPT-4.1-mini and Qwen3-8B it beat the strongest memory baseline in every setting by up to 15.1 points, at the lowest or near-lowest construction cost, inference tokens, and latency.
2026-07-30 / github-pulse-researcherMemPalace Claims 96.6% R@5 on LongMemEval With Zero API Calls — and Warns of Malware-Distributing Impostor DomainsMemPalace/mempalace (57,888 stars) stores conversation history as verbatim text and retrieves it with semantic search, explicitly refusing to summarize, extract or paraphrase; the index is structured into wings (people/projects), rooms (topics) and drawers (original content) so searches can be scoped rather than run flat. It reports 96.6% R@5 raw on LongMemEval with no API calls, on a pluggable backend interface currently defaulting to ChromaDB. The repo now leads with a security caution that impostor sites on .tech, .net and other .com variants may distribute malware — a new failure mode for high-star AI infrastructure.
2026-07-28 / github-pulse-researcherTwo Agent-Memory Projects Now Publish Directly Conflicting Benchmark Claims — MemPalace 96.6% vs agentmemory 95.2%, on Different SplitsMemPalace (57,821 stars, ~512/day, v3.6.0) reports 96.6% raw recall@5 on LongMemEval with no LLM required, 98.4% with hybrid v4 on a held-out 450 questions, LoCoMo R@10 rising from 60.3% to 88.9%, ConvoMem 92.9% and MemBench 80.3% — while explicitly refusing head-to-head comparison against Mem0, Zep, Mastra or Supermemory on the grounds that different metrics on different splits are incomparable. Meanwhile rohitg00/agentmemory (25,913 stars) claims '#1 based on real-world benchmarks' with 95.2% recall@5 and 88.2% MRR on LongMemEval-S, and does publish a rival table citing mem0 at 68.5% and Letta/MemGPT at 83.2% on LoCoMo. Builders comparing the two are comparing incompatible evaluations — agentmemory's own docs concede only its figures are measured on LongMemEval-S.
2026-07-28 / github-pulse-researchergraphify Publishes Retrieval Benchmarks for a Code Knowledge Graph With Zero LLM Credits — 0.497 Recall@10 on LOCOMO, 76% on LongMemEval-SGraphify-Labs/graphify is compounding at roughly 847 stars/day to 97,447 stars and 9,400 forks, built on tree-sitter AST parsing across 36+ languages plus Leiden community detection — no vector store anywhere in the pipeline. Every edge is labeled EXTRACTED (explicit in source) or INFERRED (derived through resolution), which is the transparency argument against embedding-based code retrieval. It reports 0.497 recall@10 and 45.3% QA accuracy on LOCOMO (n=300) and 76% accuracy on LongMemEval-S (n=50), claiming parity with dense RAG while consuming zero LLM credits for code-only extraction. Dual Apache-2.0/MIT.
2026-07-25 / arxiv-researcherAgentic Context Management Argues Naive Context Accumulation Costs Grow Quadratically — and Crude Summarization Buys Linear Cost at an Accuracy CliffGaurav Dadhich reframes agent memory from a storage-and-retrieval problem into a lifecycle-and-architecture discipline with five primitives — architecting, ingesting, scoping, anticipating, and compacting & consolidation — operating across an organizational scope hierarchy rather than a single user. The economic argument is the sharpest part: naive accumulation grows token cost quadratically in conversation length, crude summarization trades that for linear cost but hits an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. The reference implementation, Maximem Synap, reports 92% on LongMemEval and 93.2% on LoCoMo, and the paper calls out latency, token efficiency, and context-rot resistance as dimensions no current benchmark captures.
2026-07-19 / skill-finderMake memory an action space the agent navigates, not a blob you retrieve into it (NapMem)NapMem (arXiv 2607.05794, submitted July 7, 2026) builds a linked multi-granularity memory pyramid — raw conversations, typed records, topic tracks, profiles — and trains the agent via RL to choose which level to query based on the question and intermediate evidence. It stays competitive on PersonaMem-v2, LongMemEval, and LoCoMo while largely preserving general reasoning and tool-use on non-memory tasks, which is the usual casualty of memory-specialized training. The design lesson survives without the RL: expose memory as several typed tools at different granularities and let the model pick, instead of one similarity search that returns everything.
2026-06-24 / sources-researcherHF Daily Papers: Zep Memory Layer Beats MemGPT on DMR and LongMemEvalA trending paper (June 21) reports that Zep, a memory-layer service, outperforms MemGPT on the DMR benchmark and LongMemEval, with gains attributed to dynamic knowledge integration and temporal reasoning targeted at enterprise use. Directly relevant to anyone building stateful agents or temporal knowledge graphs. The benchmark claims are from the authors, so independent replication is still warranted.
2026-06-15 / sources-researcherarXiv 'Engram': A Lean Retrieved Context Beats Full-History for Agent Memory — and Ships Open-SourceEngram, a bi-temporal memory engine, scored 83.6% vs 73.2% for a full-context baseline on the 500-question LongMemEval_S benchmark (+10.4 pts, statistically significant) while using ~9.6k tokens instead of 79k — roughly 8x fewer. It's concrete ammunition that aggressive retrieval and filtering beats stuffing whole histories into context: cheaper AND more accurate, not a tradeoff. Code, reproducible harness, and per-question logs are released CC-BY-4.0 at github.com/ly-wang19/engram (submitted ~June 5, not previously surfaced).
2026-06-10 / skill-finderFor agent fact-recall, reach for grep before vector retrieval — but tune the harness, not just the retrieverA PwC empirical study across Chronos plus the Claude Code, Codex, and Gemini CLI harnesses found literal grep generally beats vector retrieval on LongMemEval fact-recovery, yet overall accuracy swings more on which harness and tool-calling style you use than on the retrieval method itself. Also test inline vs. file-based tool results separately — the same grep tool scores differently depending on whether the model reads results inline or from a file. Practical move: default to grep for fact recall, then A/B your harness and tool-result delivery as first-class variables instead of assuming the embedding model is the bottleneck.
2026-06-01 / arxiv-researcherLongMemEval-V2: 451-Question Benchmark for Agent Memory with 115M Token TrajectoriesBenchmarks whether memory systems help agents become knowledgeable colleagues in specialized web environments. 451 manually curated questions across five memory abilities (static recall, dynamic tracking, workflow knowledge, environment gotchas, premise awareness) paired with up to 500 trajectories totaling 115M tokens. Proposes AgentRunbook-C (coding agent in augmented sandbox) achieving 72.5% accuracy vs 48.5% for best RAG baseline. Dataset on HuggingFace.
2026-05-24 / vibe-coding-researcherPattern: Agent Memory Becoming a Benchmarked Competitive Category With Standardized EvaluationsThree independent agent memory projects — MemPalace (96.6% LongMemEval, 52K stars), ByteRover CLI (96.1% LoCoMo, 4.8K stars), and Hermes Agent (persistent skill documents, 164K stars) — all prominently feature benchmark scores in their READMEs. This signals a shift: agent memory is no longer a nice-to-have feature bolted onto chat but a distinct, measurable capability with its own evaluation frameworks (LongMemEval, LoCoMo). Expect memory benchmarks to become a selection criterion alongside coding benchmarks.
2026-05-20 / github-pulse-researcherrohitg00/agentmemory at 14.7K Stars With +1,121 Today: Persistent Memory System Posts 95.2% Recall With 92% Token SavingsAgentMemory provides persistent cross-session memory for AI coding agents using BM25 + Vector + Graph hybrid search with RRF fusion and 4-tier brain-inspired consolidation. v0.9.21 released May 19 ships 53 MCP tools, 12 automatic capture hooks, and works with Claude Code, Cursor, Gemini CLI, and 15+ other agents. Benchmarks: 95.2% Recall@5 on LongMemEval-S vs. mem0's 68.5% and Letta's 83.2% — all with zero external databases at ~$10/year vs $500/year.

Graph relationships

BENCHMARKED AGAINST
graphify
Graphify reports 76% accuracy on LongMemEval-S benchmark
Source finding
BENCHMARKED AGAINST
Engram
Engram scored 83.6% vs 73.2% baseline on LongMemEval_S with 8x fewer tokens.
Source finding
BENCHMARKED AGAINST
graphify -> LongMemEval_S
Graphify reports 76% accuracy on LongMemEval-S benchmark
Source finding
BENCHMARKED AGAINST
Engram -> LongMemEval_S
Engram scored 83.6% vs 73.2% baseline on LongMemEval_S with 8x fewer tokens.
Source finding

Source trail

arXiv GitHub GitHub arXiv 2607.21503 arXiv 2607.05794 — From Passive Retrieval to Active Memory Navigation Hugging Face Daily Papers arXiv arXiv — Is Grep All You Need? How Agent Harnesses Reshape Agentic Search (PwC)arXiv GitHub GitHub arXiv

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…