scriptoriumadmin/ReMe
1
0
Fork 0
mirror of https://github.com/agentscope-ai/ReMe.git synced 2026-08-28 05:25:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11
740 commits 3 branches 75 tags 131 MiB
Commit graph

740 commits

This branch
This branch
All branches
Author SHA1 Message Date
jinli.yl
70282d4110 fix(core): update version and improve compactor message handling 2026-03-04 14:10:24 +08:00
jinli.yl
58ca1f4fac fix(core): update version and enhance compactor execution with service context 2026-03-04 13:51:55 +08:00
jinliyl
5584a5c239
feat(memory): add CoPaw file-based memory system with compaction and … (#134) 
* feat(memory): add CoPaw file-based memory system with compaction and summarization

* feat(reme): add tool result cleanup and retention management

* fix(memory): resolve copaw memory processing and prompt formatting issues

* docs(reme_copaw): update documentation and initialization logic

* refactor(reme): remove override parameters from compact_tool_result

* feat(docs): update README to reflect CoPaw memory system integration

* chore(docs): update model names in documentation
 2026-03-04 10:55:43 +08:00
Jiaji
2ce002fdc2
Merge pull request #128 from zouyingcao/main 
Add FAQ.md about ReMe paper
 2026-03-03 17:13:07 +08:00
Zhouwk
fd5c06bf0d
Update Halumemeval and Longmemeval ; Update Version 0.3.0.2 (#132) 
* feat(reme): 添加配置选项以启用或禁用个人资料功能
 2026-03-03 13:11:40 +08:00
zouyingcao
c5d47da0b5
Merge branch 'agentscope-ai:main' into main 2026-03-03 12:36:18 +08:00
Jiaji
44c4ce11f3
fix pre-commit bug (#131) 2026-03-03 12:23:58 +08:00
Zhouwk
9294e65dfb
Add bool trigger on Profile memory ; Update Longmemeval Eval and HalumemEval (#129) 
* feat(reme): 添加配置选项以启用或禁用个人资料功能
 2026-03-03 11:29:49 +08:00
caozouying.czy
dc441d86a7 check pre-commit for faq.md 2026-03-03 11:26:31 +08:00
jinli.yl
ab4dbd6220 fix(embedding): disable dimensions parameter by default 2026-03-03 10:50:56 +08:00
jinliyl
652ae29464
Comment out task_name in memory summary and retrieval 2026-03-03 10:17:28 +08:00
jinliyl
a3da3215e2
Update README.md 
update readme
 2026-03-03 10:16:35 +08:00
jinli.yl
11a42d02c1 feat(embedding): add conditional dimensions parameter support for OpenAI embeddings 2026-03-02 19:27:29 +08:00
Zhouwk
eff323105f
halumem和longmemeval的Benchmark评估代码 (#124) 
* feat(benchmark): 添加 LongMemEval 评估功能和内存检索器

- 实现了 LongMemEval 数据集的评估管道
- 添加了 PersonalLongmemevalRetriever 和 PersonalLongmemevalSummarizer
- 创建了详细的统计分析工具 compute_stats.py
- 实现了完整的答案判断和准确性计算功能
- 集成了 ReMe 内存操作和查询功能
- 添加了性能指标和时间统计功能

* feat(benchmark): 添加内存准确性和完整性评估功能

- 实现了 evaluation_for_memory_accuracy 函数用于评估提取内存的准确性
- 实现了 evaluation_for_memory_integrity 函数用于评估内存完整性
- 创建了 MemoryIntegrityEvaluator 类来评估内存点覆盖情况
- 创建了 MemoryAccuracyEvaluator 类来评估提取内存的准确性
- 添加了 compute_memory_integrity_metrics 和 compute_memory_accuracy_metrics 统计函数
- 在 MetricsAggregator 中集成内存完整性和准确性指标计算
- 更新了命令行参数默认值：top_k 改为 10，batch_size 改为 16
- 重构了个人记忆汇总器中的工具循环逻辑
- 更新了评估提示词模板以支持内存质量评估
- 添加了新的检索配置和模型设置

* feat(memory): 添加个人记忆摘要器配置文件

- 新增 personal_halumem_summarizer_adddraft.yaml 配置文件
- 新增 personal_halumem_summarizer_original_backup.yaml 备份配置文件
- 实现记忆架构师系统提示和用户消息模板
- 实现个人资料代理系统提示和用户消息模板
- 支持生物特征和行为模式记忆存储
- 实现记忆去重和合并功能
- 支持用户个人资料的动态更新和删除操作

* feat(memory): 添加个人记忆摘要器配置文件

- 新增 personal_halumem_summarizer_adddraft.yaml 配置文件
- 新增 personal_halumem_summarizer_original_backup.yaml 备份配置文件
- 实现记忆架构师系统提示和用户消息模板
- 实现个人资料代理系统提示和用户消息模板
- 支持生物特征和行为模式记忆存储
- 实现记忆去重和合并功能
- 支持用户个人资料的动态更新和删除操作

* docs(readme): 添加 ReMe Memory Agent 详细介绍文档

- 创建英文版 README.md 包含核心概念、架构设计和使用指南
- 创建中文版 README_ZH.md 提供完整的本地化文档
- 介绍 Agent 驱动的记忆管理理念和层次化检索机制
- 详述项目架构包括 ReMeSummarizer 和 ReMeRetriever 组件
- 提供快速开始示例和程序化内存操作方法
- 展示 LoCoMo、LongMemEval、HaluMem 基准测试结果
- 包含完整的项目结构说明和配置要求

* chore(config): 移除配置文件中的API密钥

- 从配置文件中删除FLOW_LLM_API_KEY环境变量设置
- 移除相关的API密钥配置项
- 更新配置文档以反映新的安全实践
- 确保敏感信息不再硬编码在配置文件中
- 添加注释说明如何通过环境变量方式配置API密钥

* fix(benchmark): 修复模型调用和配置参数问题

- 修正了reme.get_llm方法的参数传递，移除冗余的name参数
- 添加了qwen3-max模型的配置支持
- 调整了默认并发数从16降至4以提高稳定性
- 修改算法版本默认值从longmemeval和v1统一为default
- 减少每类样本数量默认值从16至2以优化测试效率

* feat(benchmark): 添加记忆准确性和完整性评估功能

- 修改了 simple_request_for_json 调用以支持模型名称参数
- 新增 evaluation_for_memory_accuracy 函数用于评估记忆准确性
- 新增 evaluation_for_memory_integrity 函数用于评估记忆完整性
- 将默认模型名称从 qwen3-max 更改为 None
- 更新提取记忆逻辑以过滤 time_int 和 when_to_use 字段
- 新增 MemoryIntegrityEvaluator 类用于评估记忆完整性
- 新增 MemoryAccuracyEvaluator 类用于评估记忆准确性
- 添加 compute_memory_integrity_metrics 方法计算记忆完整性指标
- 添加 compute_memory_accuracy_metrics 方法计算记忆准确性指标
- 配置多种新 LLM 模型包括 qwen-plus-t、qwen-max-t、gpt-4o-mini 等
- 初始化完整性评估器和准确性评估器实例
- 在会话数据中添加记忆完整性和准确性评估结果
- 收集记忆完整性记录和准确性记录用于统计
- 在最终结果中包含记忆完整性和准确性指标
- 更新摘要打印方法显示记忆完整性和准确性统计信息
- 更新默认评估模型为 gpt-4o-mini-2024-07-18

* docs(readme): 删除 ReMe Memory Agent 的中英文文档

- 移除英文版 README.md 中关于 ReMe Memory Agent 的详细介绍
- 删除中文版 README_ZH.md 中关于 ReMe Memory Agent 的完整文档
- 清理了包括架构图、功能特性、快速开始和实验数据在内的所有文档内容
 2026-03-02 18:58:37 +08:00
jinli.yl
3dcb9e09f4 fix(profiles): disable thinking parameters in ReadAllProfiles tool 2026-03-02 11:53:30 +08:00
caozouying.czy
1074ec78b2 Merge branch 'main' of https://github.com/zouyingcao/ReMe 2026-03-02 11:21:07 +08:00
caozouying.czy
fe262320d3 add faq.md 2026-03-02 11:12:40 +08:00
jinliyl
3bf3dcebf4
Translate text in README from English to Chinese 2026-02-28 22:30:15 +08:00
jinliyl
0bb6321285
docs(reme): update README with comprehensive documentation for file-b… (#122) 
* docs(reme): update README
 2026-02-28 22:27:38 +08:00
jinli.yl
206da3e937 release(version): remove beta tag from version string 2026-02-28 13:49:54 +08:00
jinliyl
9298c941bc
Merge pull request #121 from agentscope-ai/dev/0227 
refactor(memory): restructure tool and procedural memory agents with …
 2026-02-27 16:20:36 +08:00
jinli.yl
c4e6225336 refactor(memory): restructure tool and procedural memory agents with enhanced capabilities 2026-02-27 16:17:22 +08:00
jinliyl
2a1953ac6b
Merge pull request #120 from agentscope-ai/dev_0227_1 
refactor(memory): integrate procedural memory into extension module
 2026-02-27 14:56:32 +08:00
jinli.yl
1d2cc36957 refactor(memory): integrate procedural memory into extension module 2026-02-27 14:55:00 +08:00
jinliyl
99c12535ca
Merge pull request #119 from zouyingcao/main 
code migration: workflow-based procedural memory (after pre-commit check)
 2026-02-27 14:47:44 +08:00
caozouying.czy
1aad787267 update service.yaml 2026-02-27 14:43:34 +08:00
zouyingcao
968d27abc4
Merge pull request #1 from zouyingcao/dev_0227 
Dev 0227
 2026-02-27 14:12:10 +08:00
caozouying.czy
bb0d0ee248 Merge branch 'main' into dev_0227 2026-02-27 14:06:11 +08:00
caozouying.czy
3760c22d45 update for pre-commit check 2026-02-27 13:30:22 +08:00
jinli.yl
e8d7c56739 feat(file_store): make embedding_model optional in base file store 2026-02-26 21:28:45 +08:00
jinli.yl
d17ac08340 refactor(schema): remove default name field from service config 2026-02-26 20:21:43 +08:00
jinliyl
0ba919cab7
Merge pull request #115 from agentscope-ai/dev_0225 
reformat 重新整理代码结构
 2026-02-26 19:13:19 +08:00
jinli.yl
370450f157 refactor(reme): remove unused context methods and update config path default 2026-02-26 18:25:38 +08:00
jinli.yl
115373ab30 refactor(benchmark): remove unused llm config and update test parameters 2026-02-26 18:20:12 +08:00
jinli.yl
23f7c51a1a refactor(core): restructure application initialization and service context 2026-02-26 17:56:59 +08:00
jinli.yl
6efecf1a3e refactor(memory): rename fs components to fb and reorganize modules 2026-02-26 16:47:04 +08:00
caozouying.czy
4ad977408e update reme.py for consistency 2026-02-26 16:06:04 +08:00
jinli.yl
8baaff9427 up 2026-02-26 15:42:26 +08:00
jinli.yl
ed133ffc30 refactor(core): restructure module organization and enhance error handling 2026-02-26 15:34:36 +08:00
jinli.yl
64b497e330 refactor(core): replace memory stores with file stores and update architecture 2026-02-26 14:18:12 +08:00
caozouying.czy
dfadfed067 update: evaluation scripts on bfcl&appworld benchmarks 2026-02-26 12:48:19 +08:00
caozouying.czy
8baefb88df merge origin/main 2026-02-26 12:33:41 +08:00
jinli.yl
40eddf442a refactor(memory_store): simplify list comprehension expressions 2026-02-25 23:39:58 +08:00
jinli.yl
bb0c2df97d refactor(memory): replace internal ChunkRecord with MemoryChunk model 2026-02-25 23:20:24 +08:00
jinli.yl
8f80cd17c1 perf(core): optimize memory store similarity search performance 2026-02-25 18:27:05 +08:00
caozouying.czy
5cbf9f3f14 update: resolve JSONDecodeError in task_memory_validation 2026-02-25 12:05:28 +08:00
caozouying.czy
4bb260ddad add safe_metadata in memory_node.py 2026-02-25 12:05:28 +08:00
caozouying.czy
7a69ec6cec update default.yaml 'flows' 2026-02-25 12:05:28 +08:00
caozouying.czy
8765d0273d update memory_deduplication.py 2026-02-25 12:05:28 +08:00
caozouying.czy
7c397603fa update paper_data format 2026-02-25 12:05:28 +08:00