datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MemoryAgentBench
🚧 Update
(Sep 29th, 2025) We updated our paper, where we removed some in-efficient and high-cost samples. We also added a sub-sample of DetectiveQA.
(July 7th, 2025) We released the initial version of our datasets.
(July 22nd, 2025) We modify the datasets slightly, adding the keypoints in LRU and change the uuid into qa_pair_ids. The question_ids is only used in Longmemeval task.
(July 26th, 2025) We fixed bug on qa_pair_ids.
(Aug.5th, 2025) We removed the… See the full description on the dataset page: https://huggingface.co/datasets/ai-hyz/MemoryAgentBench.MemoryAgentBench
🚧 Update
(Sep 29th, 2025) We updated our paper, where we removed some in-efficient and high-cost samples. We also added a sub-sample of DetectiveQA.
(July 7th, 2025) We released the initial version of our datasets.
(July 22nd, 2025) We modify the datasets slightly, adding the keypoints in LRU and change the uuid into qa_pair_ids. The question_ids is only used in Longmemeval task.
(July 26th, 2025) We fixed bug on qa_pair_ids.
(Aug.5th, 2025) We removed the… See the full description on the dataset page: https://huggingface.co/datasets/Robin076/MemoryAgentBench.multisource-memory-benchmark
Multi-Source Memory Benchmark
Status — anonymous artefact for double-blind review (NeurIPS 2026 Evaluations & Datasets Track).
Author identities, organisations, and funders are intentionally withheld until the review period concludes.
A diagnostic testbed for selective question-answering (ANSWER / SKIP) over conflicting multi-source personal memory.
Each persona has five evidence streams projected from a single latent event table with known, controlled per-source distortions… See the full description on the dataset page: https://huggingface.co/datasets/anon-neuripsed26/multisource-memory-benchmark.Dans-MemoryCore-CoreCurriculum-Small
Dan's Memory Core: Core Curriculum Small
Broad strokes
This dataset aims to provide a foundation of knowledge common to a number of fields and areas of study. The question answer pairs were generated using a RAG implementation and a curated selection of source material. Ideally this will be the first in a series of datasets that will cover a wide range of topics.
Nomic Atlas Visualiztion
Cluster visualization for the dataset available here.
Topics… See the full description on the dataset page: https://huggingface.co/datasets/PocketDoc/Dans-MemoryCore-CoreCurriculum-Small.longmemeval-cn
LongMemEval-CN 500题中文子集｜识流公开结果
这是识流维护的 LongMemEval 500题中文翻译子集与逐题评测结果。500题结果快照版本为 2026.07.15；本存档修订版为 2026.07.18，仅完善许可、引用与跨平台存档元数据，results.jsonl 未改变。
该子集状态为 draft，不是 LongMemEval 官方发布的中文版本。源自 LongMemEval 的问题与参考答案继续遵循上游 MIT License；由识流新增且有权授权的中文译文、模型输出整理、评测结果、汇总数据与原创说明采用 CC BY 4.0。完整许可边界见 NOTICE.txt。
结果摘要
测试日期：2026-07-15
总题数：500
跳过：0
首轮通过：499/500（99.8%）
独立复判：唯一未通过题复判通过
复核后有效通过：500/500
exact-match guard：298题
DeepSeek deepseek-v4-flash 判分：202题… See the full description on the dataset page: https://huggingface.co/datasets/shiliu-memory/longmemeval-cn.ISETrace-Memory-Queries
ISETrace Memory Query Corpus
This repository contains the frozen natural-language memory-query corpus used for exact-span retrieval experiments over ISETrace, an execution-grounded corpus of operating-system agent trajectories.
The release contains 6,597 English queries. Each query asks for information recoverable from one trajectory and identifies minimal answer-bearing quotes in stable source sections. Query records and authoring metadata are kept separate so metadata such as… See the full description on the dataset page: https://huggingface.co/datasets/HazeLocus/ISETrace-Memory-Queries.vln-trajectory-memory-stage2
VLN Trajectory-Memory — Stage 2 (projector alignment)
Text-only question answering where the only source of truth is a robot's action history.
Each record gives a navigation trajectory as a list of primitive actions and asks something
that can only be answered by tracking where those actions lead: how far from the start, which
way the robot faces, what happened in the last quarter of the route.
It was built to measure whether a frozen vision-language model (Qwen3-VL-2B) can read… See the full description on the dataset page: https://huggingface.co/datasets/Rithvik762/vln-trajectory-memory-stage2.omnimcp_sliding_window_memory_pruner_teaser
🔬 INSPECT THE DEEPSEEK-R1 REASONING CHAIN LIVE:
Zero hallucinations. Null syntax errors. 100% AST compiler validated.🌐 Live Interactive Reasoning & Code Inspector: https://emgena.com/trainingslager🎁 Claim your Free Starter Kit (Code: STARTER100): https://emgena.com/trainingslager🏷️ Launch Discount: Get 20 € OFF any 500-incident production suite with code LAUNCH20!
📜 Enterprise Compliance: EU AI Act Articles 50 & 53 certified • 100% DSGVO / GDPR clean • Commercial EULA… See the full description on the dataset page: https://huggingface.co/datasets/emgena/omnimcp_sliding_window_memory_pruner_teaser.MemoryCraft
MemoryCraft — Unified Agent-Memory Benchmark Collection
Five memory benchmarks reformatted into one common schema for evaluating how
well an agent uses long-term memory. Two configs:
full/ — every instance of each source, unified.
selected/ — the evaluation subset used in our runs (QA balanced across
benchmarks; Membench = its largest/long-context instances).
benchmark
full instances
full QA
selected instances
selected QA
locomo
10
1986
10
1986
longmemeval
500
500… See the full description on the dataset page: https://huggingface.co/datasets/daven3/MemoryCraft.agent-memory-benchmark
Agent Memory Compression & Evaluation Benchmark
This dataset is a controlled evaluation testbed designed to benchmark long-term memory architectures for conversational AI agents. It stress-tests how agents handle long conversations with complex fact dynamics.
Dataset Structure
1. conversation.json
A 100-turn synthetic conversation (50 user, 50 assistant turns) containing embedded facts categorized under:
Simple Facts: Baseline retrieval details.… See the full description on the dataset page: https://huggingface.co/datasets/kushalicious/agent-memory-benchmark.long-horizon-agent-memory
Long-Horizon Agent-Memory Benchmark
A benchmark for evaluating agent memory and long-horizon consistency. Each case is an
event stream (a multi-step conversation/trajectory) overlaid with stages that probe
individual memory capabilities, each carrying a failure-mode label.
Structure (40 cases, 288 stages)
events[] — the full incremental event stream (one record per line in cases.jsonl).
stages[] — a sparse scoring overlay: each stage has a capability, a probe… See the full description on the dataset page: https://huggingface.co/datasets/HieuNguyenDang/long-horizon-agent-memory.MemoryAgentBench
🚧 Update
(Sep 29th, 2025) We updated our paper, where we removed some in-efficient and high-cost samples. We also added a sub-sample of DetectiveQA.
(July 7th, 2025) We released the initial version of our datasets.
(July 22nd, 2025) We modify the datasets slightly, adding the keypoints in LRU and change the uuid into qa_pair_ids. The question_ids is only used in Longmemeval task.
(July 26th, 2025) We fixed bug on qa_pair_ids.
(Aug.5th, 2025) We removed the… See the full description on the dataset page: https://huggingface.co/datasets/Kakezh/MemoryAgentBench.recallmax-memory
RecallMax Memory Knowledge
Curated Q&A for the /recallmax slash agent — context injection, summarization,
compression, verification, and CLI workflows.
Rows: 22
Usage
from datasets import load_dataset
ds = load_dataset("lavmauryaa/recallmax-memory", split="train")
Local CLI
python scripts/recallmax.py query compression
python scripts/recallmax.py compress -i chat.txt
Categories
best_practices, cli, compression, hf, injection… See the full description on the dataset page: https://huggingface.co/datasets/lavmauryaa/recallmax-memory.