Skills2026-03-18 · source-backed

EverMemOS — Agent Memory as an Operating System.

Issue

2026-03-18

Confidence

source-backed

Sources

Redaction

passed

Story

Three-phase lifecycle: Phase 1 converts dialogue into MemCells (episodic traces + atomic facts + foresight signals); Phase 2 organizes into MemScenes with conflict resolution; Phase 3 performs MemScene-guided retrieval for minimal sufficient context. State-of-the-art on LoCoMo and LongMemEval benchmarks. arXiv

Unabyss and ZooData top Product Hunt back to back
July 17, Product Hunt's #1 product was Unabyss for Claude: shared memory across all apps and LLMs, 598 votes. July 18, #1 was ZooData: "the data layer for AI agents," 606 votes. Neither is an application. Both are substrate. (Product Hunt) One launch is noise. Two consecutive...
LycheeMemory V2 consolidates at semantic segment level and cuts construction tokens 75.9%.
arXiv 2608.12990 from Dongfang Li, Baotian Hu, Min Zhang and colleagues replaces turn-level memory consolidation with semantic boundary detection, reporting 89.22% on LoCoMo and 92.20% on LongMemEval-S while cutting construction tokens 86.0% and 75.9% versus the A-Mem baseline...
Two agent-memory projects publish directly conflicting benchmark claims on different splits.
MemPalace (57,821 stars, 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 60.3% → 88.9%, ConvoMem 92.9%, MemBench 80.3%, while explicitly refusing head-to-head comparison against Mem0,...
Lemmalog turns agent memory into a Datalog engine and beats full-transcript prompting on 38x less context.
MIT-licensed Rust, created August 27. It stores LLM observations as provenance-tracked facts with stratified rules and incremental derivation, exposed to a harness over MCP, so the model does language extraction while the database keeps logical consistency. Reported: 0.463 ±0....
graphify publishes retrieval benchmarks with zero LLM credits: 0.497 recall@10 on LOCOMO, 76% on LongMemEval-S.
Compounding at ~847 stars/day to 97,447, built on tree-sitter AST parsing across 36+ languages plus Leiden community detection, with no vector store anywhere in the pipeline. Every edge is labeled EXTRACTED (explicit in source) or INFERRED (derived through resolution), which i...
Hindsight: Biomimetic Agent Memory Hits 91% LongMemEval.
Four parallel retrieval strategies (semantic, temporal, entity, opinion) merged through cross-encoder reranking with atomic fact extraction on every write. Ships an MCP server for Claude Code adoption via single JSON config. Source

Source trail

arxiv.org/abs/2601.02163 More from arxiv.org

Entities

Agent Memory EverMemOS LoCoMo LongMemEval MemCells MemScene MemScenes Operating System Phase State

Provenance

Canonical issue: Ramsay Research Agent — March 18, 2026
AI generated: no
Story unit: 2026-03-18-evermemos-agent-memory-as-an-operating-system
Labels: source-backed, canonical briefing excerpt

Fetching from the wire…

EverMemOS — Agent Memory as an Operating System.

Story

Related stories

Unabyss and ZooData top Product Hunt back to back

LycheeMemory V2 consolidates at semantic segment level and cuts construction tokens 75.9%.

Two agent-memory projects publish directly conflicting benchmark claims on different splits.

Lemmalog turns agent memory into a Datalog engine and beats full-transcript prompting on 38x less context.

graphify publishes retrieval benchmarks with zero LLM credits: 0.497 recall@10 on LOCOMO, 76% on LongMemEval-S.

Hindsight: Biomimetic Agent Memory Hits 91% LongMemEval.

Source trail

Entities

Provenance

EverMemOS — Agent Memory as an Operating System.

Story

Related stories

Unabyss and ZooData top Product Hunt back to back

LycheeMemory V2 consolidates at semantic segment level and cuts construction tokens 75.9%.

Two agent-memory projects publish directly conflicting benchmark claims on different splits.

Lemmalog turns agent memory into a Datalog engine and beats full-transcript prompting on 38x less context.

graphify publishes retrieval benchmarks with zero LLM credits: 0.497 recall@10 on LOCOMO, 76% on LongMemEval-S.

Hindsight: Biomimetic Agent Memory Hits 91% LongMemEval.

Source trail

Entities

Provenance

Story

Related stories

Unabyss and ZooData top Product Hunt back to back

LycheeMemory V2 consolidates at semantic segment level and cuts construction tokens 75.9%.

Two agent-memory projects publish directly conflicting benchmark claims on different splits.

Lemmalog turns agent memory into a Datalog engine and beats full-transcript prompting on 38x less context.

graphify publishes retrieval benchmarks with zero LLM credits: 0.497 recall@10 on LOCOMO, 76% on LongMemEval-S.

Hindsight: Biomimetic Agent Memory Hits 91% LongMemEval.

Tomorrow's issue, in your inbox.

Source trail

Entities

Provenance

Story

Related stories

Unabyss and ZooData top Product Hunt back to back

LycheeMemory V2 consolidates at semantic segment level and cuts construction tokens 75.9%.

Two agent-memory projects publish directly conflicting benchmark claims on different splits.

Lemmalog turns agent memory into a Datalog engine and beats full-transcript prompting on 38x less context.

graphify publishes retrieval benchmarks with zero LLM credits: 0.497 recall@10 on LOCOMO, 76% on LongMemEval-S.

Hindsight: Biomimetic Agent Memory Hits 91% LongMemEval.

Tomorrow's issue, in your inbox.

Source trail

Entities

Provenance