Release V2.0.0

What's Changed

• feat: simplify simple tree by @CaralHsi in #461
• feat: max worker by @CaralHsi in #475
• Feat/dedup mem by @Wang-Daoji in #473
• feat: add topk for working mem by @fridayL in #476
• feat: update readme by @fridayL in #477
• feat: change url by @fridayL in #478
• fix: chat time issue 2023->2025 by @whipser030 in #479
• scheduler feat: implementation of redis queue and new api search functions of mixture and fine mode by @tangg555 in #462
• feat: update readme by @fridayL in #481
• add pool health && log by @wustzdy in #482
• Feat: reorganize playground code and merge to API by @fridayL in #488
• Fix/no response by @CarltonXiang in #490
• fix lack mem_cube_id bug in pref async by @Wang-Daoji in #494
• Feat/fix explicit threshold by @Wang-Daoji in #495
• Feat：reorg playground code by @fridayL in #497
• Feat: add redis_scheduler by @fridayL in #499
• Update API Reference link in README.md by @CarltonXiang in #500
• hotfix bug in pref init by @Wang-Daoji in #502
• feat & refactor: add searcher to handler_init and remove logger info from get_messages by @tangg555 in #501
• feat: log support time rotating by @CarltonXiang in #504
• fix init bug pref by @Wang-Daoji in #508
• Feat/log rotating by @CarltonXiang in #507
• fix: format error by @CarltonXiang in #510
• Dev by @CaralHsi in #496
• Feature/playground memcube log structured logs by @glin93 in #509
• feat: sync change by @fridayL in #512
• hotfix:hotfix by @fridayL in #513
• feat: abstract CubeView to Add & Search Handler by @CaralHsi in #498
• Feat/merge api refactor to dev by @Wang-Daoji in #514
• Feature/memcube log structured logs rework by @glin93 in #516
• feat: enhance APIADDRequest with custom_tags, info, and is_feedback fields by @CaralHsi in #515
• feat: add headers for embedding and reranker by @fridayL in #519
• docs: update .env.example with comprehensive variables and comments by @fancyboi999 in #511
• refactor: Consolidate backward compatibility into API models; simplify handler logic by @CaralHsi in #520
• Feat: add deepsearch agent for memos by @fridayL in #517
• add status of reasoning in playground by @Wang-Daoji in #523
• Feat: deepsearch agent dock search pipeline by @fridayL in #524
• Feat/join test playground by @Wang-Daoji in #527
• Feat: update prompt and format need raw by @fridayL in #528
• fix: cube init by @fridayL in #529
• Feat/redis scheduler by @glin93 in #526
• feat: add full text memory by jieba by @fridayL in #532
• Feat： update code by @fridayL in #533
• fa_bu_hui pref by @Wang-Daoji in #534
• Feat/merge api refactor to dev by @Wang-Daoji in #531
• fix: remove by @fridayL in #535
• feat: enable multi-cube chat (read/write) & unify ChatRequest/ADDRequest normalization by @CaralHsi in #521
• feat: Multi-Model Memory Reader with Modular Parser Architecture by @CaralHsi in #536
• feat(qdrant):support qdrant cloud and add index by @fancyboi999 in #522
• Feat: remove dup func name and add agentic search by @fridayL in #537
• fix: Make from_memory_type and to_memory_type optional and add task_i… by @glin93 in #538
• fix: log timeRotating by @CarltonXiang in #539
• Feat/merge api refactor to dev by @Wang-Daoji in #542
• update pool size by @wustzdy in #545
• Feat: add full text mem by @fridayL in #544
• feat: fix tiny parameter bug in multi model reader and add a multi-model memreader example by @CaralHsi in #546
• Fix scheduler logger memory size retrieval by @glin93 in #547
• Feat/task id query monitoring by @glin93 in #548
• Feat/merge api refactor to dev by @Wang-Daoji in #549
• Feat/add pref threshold by @Wang-Daoji in #550
• Dev 1.0.1 zdy like by @wustzdy in #551
• Feat: add func Base class and add strategy logs, low search mode by @fridayL in #552
• Fix/async add logging by @glin93 in #554
• hotfix: align KB knowledgeBaseUpdate logs with spec by @glin93 in #555
• Feat/merge api refactor to dev by @Wang-Daoji in #556
• feat: multimodal reader by @CaralHsi in #560
• delete_node_by_prams for filter && simple support by @wustzdy in #558
• Feat/multi model reader by @CaralHsi in #561
• feat: add filter for search_memories by @endxxxx in #553
• fix contains by @wustzdy in #564
• fix full_fields by @wustzdy in #566
• feat: complete multi modal by @CaralHsi in #562
• Hot func main/delete memory by @Wang-Daoji in #565
• Feat: sync hotfix to dev and add full text for polardb by @fridayL in #563
• update delete_node_by_prams add delete_node_by_prams by @wustzdy in #568
• Feat: insert fulltext search into pipeline by @fridayL in #567
• feat/complete multi modal by @CaralHsi in #570
• feat: feedback interface by @whipser030 in #541
• Feat/merge api refactor to dev by @Wang-Daoji in #569
• Feat/redis scheduler: task broker + orchestrator + new scheduler monitor by @tangg555 in #571
• Remove dump.rdb by @glin93 in #576
• Feat: add langchain markdown chunker by @fridayL in #574
• Debug scheduler by @tangg555 in #577
• Feat/file parser debug by @CaralHsi in #572
• fix function log_add_messages by @glin93 in #582
• Dev zdy delete 120002 by @wustzdy in #580
• feat: timer add log args by @CarltonXiang in #581
• Scheduler by @tangg555 in #584
• Scheduler: fix bugs due to init from env by @tangg555 in #585
• Fix: submit add for playground query by @fridayL in #586
• feat(scheduler): Propagate trace_id across process boundaries for mem… by @tangg555 in #592
• Feat/add model log by @CarltonXiang in #595
• Scheduler: new feat to addressed repeated task issues by @tangg555 in #594
• feat: split chunk for pure string by @CaralHsi in #593
• Fix dequeue timestamp logging for pydantic models by @glin93 in #596
• feat: Feedback Function by @whipser030 in #597
• Feat/tool memory by @Wang-Daoji in #583
• Hotfix/cloud log handler by @glin93 in #598
• fix(scheduler): Correctly process feedback logs by checking for 'text… by @glin93 in #600
• chore(feedback): propagate source_doc_id in KB logs if available by @glin93 in #601
• feat: add delete memory log; fix decode sources by @CaralHsi in https://github.com...

Release v1.1.3

What's Changed

• add: change deafult pre_load by @fridayL in #338
• feat: add memory size in product api by @CaralHsi in #348
• Feat: update load cubes by @fridayL in #350
• eat:reoganize prompt with reference in user content by @kakack in #351
• hotfix:noe4j community dataformat by @fridayL in #353
• milvus implement by @Wang-Daoji in #354
• fix: code ruff format by @fridayL in #355
• Fix/remove bug by @CaralHsi in #356
• Fix/api client by @CarltonXiang in #357
• chore: bump version to v1.1.2 by @tangg555 in #360
• fix: remove old mem by @CaralHsi in #361
• feat: only single-db mode in nebula now; modify index gql for better efficiency by @CaralHsi in #363
• feat: add server api prd by @fridayL in #362
• Feat: add neo4j db for user_name by @fridayL in #365
• Feat: add chat complete for new server_api by @fridayL in #366
• fix: nebula efficiency by @CaralHsi in #369
• Feat/merge dev by @fridayL in #374
• Feat: sync test to dev by @fridayL in #375
• Eval scripts by @Nyakult in #377
• feat: merge dev into main and change api-server by @fridayL in #376
• fix: sqlite list users error by @fridayL in #384
• feat: introduce async memory add for TreeTextMemory using MemScheduler by @CaralHsi in #373
• add pm and pref eval scripts by @Nyakult in #385
• Meger update about scheduler and new api to Dev by @tangg555 in #386
• Feat/merge inst cplt to dev by @Wang-Daoji in #388
• Feat: add reranker strategies and update configs by @fridayL in #390
• modify code in evaluation by @Wang-Daoji in #392
• fix bug in pref_mem return by @Wang-Daoji in #399
• add polardb by @wustzdy in #395
• feat: fix mode by @lijicode in #400
• Feat: remove long waring for internet and add content for memreader by @fridayL in #401
• feat: redis for sync history memories and new api of mixture search by @tangg555 in #398
• memos online api eval scripts and readme by @Nyakult in #403
• feat: fix sources by @lijicode in #404
• fix porlar by @lijicode in #406
• Feat/arms by @CarltonXiang in #402
• Hotfix: memos playground prompt reverse by @fridayL in #408
• Feat/pref optimize update by @Wang-Daoji in #409
• feat: fix polardb graph by @lijicode in #411
• feat: async add api by @CaralHsi in #410
• use nacos by @lijicode in #407
• feat: async add api by @CaralHsi in #413
• revision of mixture api: add conversation turn and reduce 2 stage ranking to 1 stage by @tangg555 in #405
• Feat: add recall strategy by @whipser030 in #414
• Revert "Feat: add recall strategy " by @CaralHsi in #415
• Feat： add new recall and verify by @fridayL in #416
• Feat: remove usage data by @fridayL in #417
• feat: add moniter schedule by @CaralHsi in #419
• feat:turn off graph call by @whipser030 in #418
• pm & prefEval scripts updates by @Nyakult in #421
• add polardb pool by @wustzdy in #420
• Feat/pref optimize update by @Wang-Daoji in #422
• fix:tree file change Searcher inputs by @whipser030 in #423
• Feat/pref optimize update by @Wang-Daoji in #425
• Fix/query schedule by @CaralHsi in #424
• fix: message schema bug by @CaralHsi in #426
• fix commit by @wustzdy in #427
• Feat/pref optimize update by @Wang-Daoji in #429
• Feat/pref optimize update by @Wang-Daoji in #431
• Feat/pref optimize update by @Wang-Daoji in #432
• Feat/add request log by @CarltonXiang in #439
• Feat/standardized preference field by @Wang-Daoji in #440
• update polardb pool timeout by @wustzdy in #441
• feat: fix self-input prompt error by @fridayL in #443
• feat: fix polardb value by @lijicode in #445
• Feat/add request log by @CarltonXiang in #442
• Feat/revert request context by @CarltonXiang in #446
• fix prompt error by @Wang-Daoji in #447
• fix: fix search config input bug; patch retrieve_utils path set; adjust reader strategy template. by @whipser030 in #448
• eval result by @Nyakult in #428
• Useless quotes by @wustzdy in #450
• Revert "fix prompt error" by @CaralHsi in #452
• Revert "fix: fix search config input bug; patch retrieve_utils path set; adjust reader strategy template." by @CaralHsi in #453
• Revert "Useless quotes" by @CaralHsi in #454
• fix prompt error by @Wang-Daoji in #455
• Feat/remove pref rank prompt by @Wang-Daoji in #456
• fix: fix strategy reader input; code reformat by @whipser030 in #457
• Dev ccl1103 by @lijicode in #449
• Feat/fix bug 1031 by @Wang-Daoji in #459
• Fix/no response by @CarltonXiang in #463
• doc: Update readme by @Nyakult in #458
• Fix/no response by @CarltonXiang in #464
• Fix: fix pg query for group error string by @fridayL in #465
• feat: freeze usage update in Searcher by @CaralHsi in #466
• feat: API1.1 by @CaralHsi in #434
• doc: update readme by @CaralHsi in #469
• chore: bump version to v1.1.3 by @CaralHsi in #470
• chore: bump version to v1.1.3 by @CaralHsi in #471

New Contributors

• @Wang-Daoji made their first contribution in #354
• @wustzdy made their first contribution in #395
• @whipser030 made their first contribution in #414

Full Changelog: v1.1.2...v1.1.3

Release v1.1.2

What's Changed

• fix: api client get_message models by @CarltonXiang in #359

Full Changelog: v1.1.1...v1.1.2

Release v1.1.1

What's Changed

• feat: delete custom_logger_handler by @CarltonXiang in #289
• fix: change env model name by @fridayL in #292
• fix:#286:#286 by @kakack in #293
• Feat:add self defined memcube id for reg user by @fridayL in #295
• Feat/add opentelmetry by @CarltonXiang in #298
• feat: add orginal context for reranking by @fridayL in #284
• revert: nebular require_python by @CarltonXiang in #300
• feat: chat bot api by @CaralHsi in #294
• feat: chat bot api by @CaralHsi in #302
• feat: chat bot api, add reranker filter; fix pydantic bug by @CaralHsi in #303
• fix: bug in internet pydantic error by @CaralHsi in #304
• Feat/add opentelmetry by @CarltonXiang in #307
• feat: update nebula to nebula 5.1.1 by @CaralHsi in #311
• fix: nebula multi db bug by @CaralHsi in #313
• Feat/memos client by @CarltonXiang in #312
• Feat: add time log for threaddict and change openai packacge singleton by @fridayL in #314
• Feat/add timerlog by @fridayL in #317
• Feat/add opentelmetry by @CarltonXiang in #315
• feat: add api client by @CarltonXiang in #316
• Feat: add segment lock dict by @fridayL in #319
• fix:fix dump parallel for dumps cubes by @fridayL in #320
• feat: add sinlgleton by @fridayL in #321
• feat: nebula&reorganize update by @CaralHsi in #322
• fix: nebula reset bug by @CaralHsi in #323
• feat: add default processing in mem-reader by @CaralHsi in #325
• feat:add time step by @fridayL in #326
• Feat:add time step by @fridayL in #327
• docker start by @pursues in #324
• Feat: remove json by @fridayL in #328
• feat: remove by @fridayL in #329
• fix: not include embedding by @CaralHsi in #330
• Feat/add time step by @fridayL in #331
• Feat/add time step by @fridayL in #332
• Fix/default add by @CaralHsi in #333
• feat: recall and searcher use parallel by @lijicode in #337
• Feat/api client by @CarltonXiang in #334
• feat: API 1.0 by @CarltonXiang in #339
• fix: format by @CaralHsi in #341
• chore: bump version to v1.1.0 by @CaralHsi in #340

New Contributors

• @pursues made their first contribution in #324

Full Changelog: v1.0.1...v1.1.1

Release v1.1.0

What's Changed

• feat: delete custom_logger_handler by @CarltonXiang in #289
• fix: change env model name by @fridayL in #292
• fix:#286:#286 by @kakack in #293
• Feat:add self defined memcube id for reg user by @fridayL in #295
• Feat/add opentelmetry by @CarltonXiang in #298
• feat: add orginal context for reranking by @fridayL in #284
• revert: nebular require_python by @CarltonXiang in #300
• feat: chat bot api by @CaralHsi in #294
• feat: chat bot api by @CaralHsi in #302
• feat: chat bot api, add reranker filter; fix pydantic bug by @CaralHsi in #303
• fix: bug in internet pydantic error by @CaralHsi in #304
• Feat/add opentelmetry by @CarltonXiang in #307
• feat: update nebula to nebula 5.1.1 by @CaralHsi in #311
• fix: nebula multi db bug by @CaralHsi in #313
• Feat/memos client by @CarltonXiang in #312
• Feat: add time log for threaddict and change openai packacge singleton by @fridayL in #314
• Feat/add timerlog by @fridayL in #317
• Feat/add opentelmetry by @CarltonXiang in #315
• feat: add api client by @CarltonXiang in #316
• Feat: add segment lock dict by @fridayL in #319
• fix:fix dump parallel for dumps cubes by @fridayL in #320
• feat: add sinlgleton by @fridayL in #321
• feat: nebula&reorganize update by @CaralHsi in #322
• fix: nebula reset bug by @CaralHsi in #323
• feat: add default processing in mem-reader by @CaralHsi in #325
• feat:add time step by @fridayL in #326
• Feat:add time step by @fridayL in #327
• docker start by @pursues in #324
• Feat: remove json by @fridayL in #328
• feat: remove by @fridayL in #329
• fix: not include embedding by @CaralHsi in #330
• Feat/add time step by @fridayL in #331
• Feat/add time step by @fridayL in #332
• Fix/default add by @CaralHsi in #333
• feat: recall and searcher use parallel by @lijicode in #337
• Feat/api client by @CarltonXiang in #334
• feat: API 1.0 by @CarltonXiang in #339
• fix: format by @CaralHsi in #341
• chore: bump version to v1.1.0 by @CaralHsi in #340

New Contributors

• @pursues made their first contribution in #324

Full Changelog: v1.0.1...v1.1.0

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！