Release v1.0.1

What's Changed

• feat: use different template for different language input by @Nyakult in #232
• fix: time hullucination by @CaralHsi in #234
• fix: chat time bug by @CaralHsi in #235
• push locomo rag eval code by @CSLiuPeng in #180
• feat: add further questions for dialogue by @fridayL in #236
• Fix: fix list user bugs and multi-user-examples get_all args by @fridayL in #237
• fix: nebula bug by @CaralHsi in #242
• Feat: change reference position and reorganize code by @fridayL in #240
• feat: reject answer by @CaralHsi in #243
• feat: support retrieval from specified memos_cube by @CaralHsi in #244
• feat: modify product answer prompt by @CaralHsi in #245
• feat: modify reference format by @CaralHsi in #246
• feat: memos add moscube turnoff by @fridayL in #247
• Fix: fix memcube path bug for docker and change further question prompt by @fridayL in #248
• Feat: add chat complete api for no-stream and rewrite chat func for moscore by @fridayL in #253
• fix: mem-reader bug by @CaralHsi in #255
• feat: modify nebula session pool by @CaralHsi in #259
• fix: general_text add user_id by @fridayL in #260
• feat: Asynchronous processing of logs, notifications and memory addit… by @lijicode in #261
• feat: mos add load sdk for user by @fridayL in #263
• feat: enhance NebulaGraph pool management & improve Searcher usage logging by @CaralHsi in #265
• feat: add custom logger by @CarltonXiang in #217
• Feat: update chatbot for postprocessing memory by @fridayL in #267
• Feat/add traceid by @CarltonXiang in #270
• feat: modify mem-reader prompt by @CaralHsi in #273
• Feat/add traceid by @CarltonXiang in #274
• Feat: fix stream output and add openai stream by @fridayL in #276
• feat: add reranker by @CaralHsi in #277
• fix: reranker config bug by @CaralHsi in #278
• feat: adjust similarity threshold by @CaralHsi in #279
• feat: set minimun returned memories back to 3 by @CaralHsi in #280
• Feat: change mem prompt by @fridayL in #281
• feat: internet search speed and reranker by @CaralHsi in #282
• feat: update filter mem by @fridayL in #285
• feat: updatebug by @fridayL in #287
• feat: modify self intro by @CaralHsi in #288
• Chore: Change version to v1.0.1 by @fridayL in #290
• chore: bump version to v1.0.1 by @CaralHsi in #275

New Contributors

• @CSLiuPeng made their first contribution in #180
• @lijicode made their first contribution in #261

Full Changelog: v1.0.0...v1.0.1

Release v1.0.0

What's Changed

• update readme by @tangg555 in #194
• fix: nebula multi-embedding & add BochaAI Search Retriever by @CaralHsi in #195
• feat: modify product config by @CaralHsi in #199
• fix: fix bug when calling _concat_caches in kv.py (from pr#177) by @spitzblattr in #205
• Feat/reorg dev by @Nyakult in #202
• feat: enhance retriever, reorganizer & NebulaGraph handling by @CaralHsi in #200
• feat & refactor: add search function feature to test scheduler on a modified locome benchmark, and slightly change the logic of query consume and query monitors by @tangg555 in #204
• feature & fix bugs: fix bugs after removing initialize_working_memory_monitors; add dispatcher_monitor designed to monitor the thread pool in the dispatcher moduler, and meanwhile dispatcher is enhanced with thread issue handlers by @tangg555 in #207
• feat: add custom request log by @CarltonXiang in #206
• fix: a temporal workaround for the "virtualenv 20.33.0 breaks Poetry in GitHub Actions" by @Ki-Seki in #213
• chore: The Poetry virtualenv issue persists; another temporary workaround is ok by @Ki-Seki in #215
• fix: reference for some string by @fridayL in #211
• fix: self.mem_cubes RuntimeError: dictionary changed size during iteration by @fridayL in #216
• feat: add embedding-aware graph query interfaces and parallel retrieval by @CaralHsi in #212
• feat: delete-custom-logger by @CarltonXiang in #220
• Refactor: Conflict resolution, bug fixes mainly for the mem scheduler by @tangg555 in #221
• feat: fix illumination by @CaralHsi in #222
• fix: reorganize and schedular bug by @CaralHsi in #223
• MemOS v0.2.3 release by @kakack in #225
• fix: remove field name will cause error for org-memscheduler config by @fridayL in #226
• MemOS v0.2.3 release by @kakack in #227
• feat: illumination by @CaralHsi in #229
• Chore: Change version to v1.0.0 by @kakack in #230
• chore: bump version to v1.0.0 by @kakack in #228

New Contributors

• @spitzblattr made their first contribution in #205
• @CarltonXiang made their first contribution in #206

Full Changelog: v0.2.2...v1.0.0

Release v0.2.2

What's Changed

• feat: reorganizer config code and add remove dup nodes for playground-demo by @fridayL in #135
• refactor: improve architecture and configurations for memory scheduler by @tangg555 in #142
• fix: date parse error and fix memreader by @Nyakult in #132
• fix: General text memory by @Nyakult in #140
• feat: add try catch for mem scheduler by @fridayL in #144
• Feat: docker settings modify by @tianxing02 in #143
• fix bugs: fix bugs in the example of memos_w_scheduler and fix bugs o… by @tangg555 in #147
• feat(eval): support memos api mode by @Duguce in #116
• feat: modify internet search by @CaralHsi in #152
• feat: add context for playground and for fastapi object by @fridayL in #151
• feat: add memreader to tackle with internet by @CaralHsi in #154
• feat: check nodes existence by @Nyakult in #156
• feat: add code for internet api and change deault config for memos by @fridayL in #155
• fix: align MOSProduct._build_system_prompt signature with MOSCore by @muzzlol in #146
• feat: add user manager factory pattern and product API enhancements by @fridayL in #166
• feat: add Nebula by @CaralHsi in #168
• fix: align MOSProduct._build_system_prompt signature with MOSCore by @CaralHsi in #169
• feat: update neublar config and change user manager dup field for mysql by @fridayL in #171
• Feat/rewrite query by @endxxxx in #149
• fix: fine search bug when calling nebula by @CaralHsi in #181
• fix: add metadata filter and get by metadata bug by @tianxing02 in #184
• feat: update dim env by @fridayL in #186
• Feat/chat history by @endxxxx in #187
• update version by @tangg555 in #188
• rebase main by @tangg555 in #190
• chore: bump version number to v0.2.2 by @fridayL in #191

New Contributors

• @tangg555 made their first contribution in #142
• @muzzlol made their first contribution in #146
• @endxxxx made their first contribution in #149

Full Changelog: v0.2.1...v0.2.2

Release v0.2.1

What's Changed

• fix: reorganizer bug by @CaralHsi in #64
• Feat: add volcengine embedding support by @ioo0s in #57
• Fix/general text memory. embed one sentence by @J1awei-Yang in #76
• feat: add neo4j share-db example by @CaralHsi in #59
• Feat/api embedding by @CaralHsi in #81
• feat: Add embedder consistency validation with warning and tests by @Dustyposa in #69
• Feat: add demo api and scheduler vllm etc by @fridayL in #83
• feat: add download_examples command by @Ki-Seki in #87
• feat: add stale issue and PR management workflow by @Ki-Seki in #89
• feat: update issue and pr templates by @Ki-Seki in #98
• Add More backend by @Gaojianli in #99
• feat: add multi language by @CaralHsi in #92
• feat(eval): add longmemeval evaluation pipeline by @Duguce in #104
• Feat：change deafult config for product by @fridayL in #108
• Support customized system prompt base by @newmeta-ben in #102
• feat: recursively cluster nodes to max_cluster_size by @Nyakult in #105
• feat: return ids when add memory by @CaralHsi in #119
• Feat: add simple memos for user could easy start by @fridayL in #118
• Feat: More Llm API by @CaralHsi in #113
• feat: update doc mem reader by @Nyakult in #123
• build: optimize dependencies management by @Ki-Seki in #120
• Fix None issue in reorganizer queue by @J1awei-Yang in #125
• feat: update PR template to include documentation issue/PR link by @Ki-Seki in #126
• Feat:add mcp serve support and client demo by @fridayL in #127
• Feat: neo4j community by @CaralHsi in #121
• feat(example): add MOSProduct multi-user locomo example with shared Neo4j database by @CaralHsi in #109
• fix: update Python version constraints in project files by @Ki-Seki in #129
• feat: one-click deployment with docker by @tianxing02 in #133
• chore: bump version number to v0.2.1 by @fridayL in #131

New Contributors

• @ioo0s made their first contribution in #57
• @J1awei-Yang made their first contribution in #76
• @Dustyposa made their first contribution in #69
• @newmeta-ben made their first contribution in #102
• @tianxing02 made their first contribution in #133

Full Changelog: v0.2.0...v0.2.1

Release v0.2.0

We are thrilled to officially release MemOS v0.2.0 (Stellar, 星河), an early preview version of MemOS v1.0.

MemOS is an operating system for Large Language Models (LLMs) designed to enhance their long-term memory capabilities. This framework enables LLMs to store, retrieve, and manage information, facilitating more context-aware, consistent, and personalized interactions.

The current release includes the following features:

• Support for CRUD operations across three memory layers: Memory Manager, MemCube, and MemOS
  • The Memory Manager currently supports: General Memory Management, Tree Memory Management, and KV Cache Memory Management
  • MemCube integrates three memory types (Textual Memory, Activation Memory, and Parametric Memory), representing similar memory contents through different storage formats
  • MemOS serves as the top-level abstraction for managing multiple MemCubes
• MemOS Capabilities
  • Basic chat functionality with LLMs through MemOS
  • Offline batch document loading and parsing into MemCubes
• FastAPI interface for the MemOS layer
• Preliminary MemScheduler functionality
• Various infrastructure components including LLM, Embedder, Neo4j graph DB, Qdrant vector DB, Parser, and Chunker

Note: This is currently a preview version with known limitations and bugs. We welcome contributions from the community!

What's Changed

• refactor: update feature request template by @Ki-Seki in #50
• docs: update documentation links and images by @Ki-Seki in #55
• feat: add structure reorganizer and conflict resolver by @CaralHsi in #14
• feat(eval): add openai memory on locomo - eval guide by @Duguce in #54
• feature: mem reader update and some bug fixs by @Nyakult in #43
• chore: bump version number to v0.2.0 by @fridayL in #66

New Contributors

• @CaralHsi made their first contribution in #14
• @Nyakult made their first contribution in #43

Full Changelog: v0.1.13...v0.2.0

我们很高兴正式发布 MemOS v0.2.0 (Stellar, 星河)，这是 MemOS v1.0 的早期预览版本。

MemOS 是一个专为大型语言模型（LLMs）设计的操作系统，旨在增强其长期记忆能力。该框架使 LLMs 能够存储、检索和管理信息，促进更具上下文感知、一致性和个性化的交互。

当前版本包含以下功能：

• 支持三个内存层的 CRUD 操作：Memory Manager、MemCube 和 MemOS
  • Memory Manager 目前支持：通用内存管理、树形内存管理和 KV 缓存内存管理
  • MemCube 集成了三种内存类型（文本内存、激活内存和参数内存），通过不同的存储格式表示相似的内存内容
  • MemOS 作为管理多个 MemCubes 的顶层抽象
• MemOS 功能
  • 通过 MemOS 与 LLMs 的基本聊天功能
  • 离线批量文档加载和解析到 MemCubes
• MemOS 层的 FastAPI 接口
• 初步的 MemScheduler 功能
• 各种基础设施组件，包括 LLM、嵌入器、Neo4j 图数据库、Qdrant 向量数据库、解析器和分块器

注意：这是目前的预览版本，存在已知的限制和错误。我们欢迎社区的贡献！

Release v0.1.13

What's Changed

• ci: add issue templates and update pull request template by @Ki-Seki in #17
• Add long version of MemOS paper by @Ki-Seki in #20
• docs: update citations by @Ki-Seki in #25
• feat(eval): add eval configs example by @Duguce in #19
• feat(eval): add run locomo eval script by @Duguce in #28
• fix(example): correct ParsedTaskGoal usage and add unrelated memory for testing by @Wujiaxuan007 in #23
• style: fix format by @Ki-Seki in #36
• ci: Include macOS and Windows in CI pipeline by @Ki-Seki in #22
• docs: move all docs to https://github.com/MemTensor/MemOS-Docs by @Ki-Seki in #34
• fix(eval): delete about memos redundant search branches by @Duguce in #35
• feat: add internet retrieval and CoT functionality to MemOS by @fridayL in #16
• docs: update pull request template for clarity and completeness by @Ki-Seki in #45
• chore: bump version to v0.1.13 by @fridayL in #47
• chore: bump version to v0.1.13 by @fridayL in #48

New Contributors

• @Ki-Seki made their first contribution in #17
• @Duguce made their first contribution in #19
• @Wujiaxuan007 made their first contribution in #23

Full Changelog: v0.1.12...v0.1.13

Release v0.1.12 (pre-release)

Full Changelog: https://github.com/MemTensor/MemOS/commits/v0.1.12