v0.1.0

What's Changed

• remove duplicate step being entered into prompt for MathAgent by @peteryschneider in #9
• feat: add running arguments for mixtral-8x7b-it by @dongyuanjushi in #10
• Update README.md by @eltociear in #11
• chore: Update flow.py by @eltociear in #15
• Update README.md by @agiresearch in #16
• doc: add instructions of how to contribute by @dongyuanjushi in #17
• docs: fix link by @JHSUYU in #18
• doc: update README.md with max python version by @1tylermitchell in #19
• Update README.md by @agiresearch in #20
• Delete AIOS.pdf by @agiresearch in #21
• docs: add reference to pre-commit and pytest by @dongyuanjushi in #22
• chore: add pre-commit check by @dongyuanjushi in #23
• add test code and dependencies via pytest by @dongyuanjushi in #25
• test: add memory test by @JHSUYU in #26
• Update README.md by @agiresearch in #27
• Update README.md by @agiresearch in #28
• Update README.md by @agiresearch in #29
• test: add test for rapid api calling by @dongyuanjushi in #30
• refactor: add shell simulator and customized logger by @dongyuanjushi in #31
• Update simulator.py by @eltociear in #32
• Update README.md by @agiresearch in #33
• Update README.md by @agiresearch in #34
• Update README.md by @agiresearch in #35
• Update README.md by @agiresearch in #36
• feat: add agent ID recycler by @dongyuanjushi in #37
• fix: deployment mode printing only to the file by @dongyuanjushi in #38
• feat: add gpt-3.5-turbo and gpt-4 as llm backbone by @dongyuanjushi in #40
• docs: add support of gpt-3.5 and gpt-4 by @dongyuanjushi in #41
• Update README.md by @evison in #42
• fix: address logger output issue by @dongyuanjushi in #43
• Update README.md by @agiresearch in #44
• Update README.md by @agiresearch in #45
• Update README.md by @agiresearch in #46
• add workflow for MathAgent and adjust print format by @dongyuanjushi in #47
• feat: Support Amazon Bedrock-provided models ⛰️ by @JGalego in #48
• Merge branch 'agiresearch:main' into 'agiresearch:dev' by @dongyuanjushi in #49
• docs: update contributors and how to contribute by @dongyuanjushi in #51
• Update README.md by @agiresearch in #52
• refactor: move native workflow of constructing agents into the native-agent branch by @dongyuanjushi in #53
• update dev branch by @dongyuanjushi in #55
• fix: context switch of RR scheduler by @dongyuanjushi in #57
• [fix] raise Error in llms by @lumiere-ml in #58
• add new features and update logging style by @dongyuanjushi in #59
• refactor: typo in RecAgent.json by @eltociear in #60
• add docs and refactor code by @dongyuanjushi in #61
• test by @dongyuanjushi in #62
• update dev branch by @dongyuanjushi in #64
• [Core] Refactor llms code using OOP, and model registry by @lumiere-ml in #65
• llm refactor by @dongyuanjushi in #66
• add test for the refactored llm registration by @dongyuanjushi in #67
• [chore]: Adding CVE dependency checks for requirements.txt via pre-commit recommended hooks by @ivanbelenky in #69
• update the main branch from dev by @dongyuanjushi in #68
• Refactored LLMs to make them dynamic & added in-memory provider segmentation by @BRama10 in #70
• add customized logger by @dongyuanjushi in #72
• add customized logger by @dongyuanjushi in #73
• add logger by @dongyuanjushi in #74
• add console logger by @dongyuanjushi in #75
• [docs] update README.md by @dongyuanjushi in #77
• update News by @dongyuanjushi in #78
• Update README.md by @agiresearch in #79
• merge llm-refactor branch by @dongyuanjushi in #80
• docs: Corrected gramatical error by @JUSTSUJAY in #81
• add more rapid api tools by @dongyuanjushi in #82
• add more tools by @dongyuanjushi in #83
• add more llm backbones by @dongyuanjushi in #84
• Memory management by @JHSUYU in #86
• [feat] add more tools by @dongyuanjushi in #87
• [feat] add LRU-k replacer by @dongyuanjushi in #88
• refactor: update command_parser.py by @eltociear in #89
• [refactor] update logger and cache cleaner by @dongyuanjushi in #90
• [core] update dev branch by @dongyuanjushi in #91
• [fix] update logger by @dongyuanjushi in #92
• refactor: move agents and tools to OpenAGI by @Tata0703 in #94
• feat: add scheduler evaluation by @dongyuanjushi in #96
• update readme and add bash scripts by @Tata0703 in #97
• refactor: set down queue scanning time by @dongyuanjushi in #98
• refactor: remove redundant llm config files and update llm name in README by @dongyuanjushi in #99
• 1. add dotenv, 2) add timing logic for concurrent and sequential exec… by @Tata0703 in #100
• fix: waiting time and turnaround time calculation by @dongyuanjushi in #101
• feat: add vllm module by @dongyuanjushi in #102
• Revert "feat: add vllm module" by @Tata0703 in #103
• update README by @dongyuanjushi in #104
• enable ollama by @Tata0703 in #108
• ignore dotenv by @zzfoo in #111
• update readme by @Tata0703 in #112
• make pytest work on CPU by @Tata0703 in #113
• docs: fix readme by @Tata0703 in #115
• feat: add tool calling for chatgpt-based math agent by @dongyuanjushi in #116
• refactor: remove duplicated code by @ArnoldIOI in #118
• Update README.md by @agiresearch in #119
• feat: Add gpt-4o model to model registry by @itsthemoon in #122
• feat: Add TravelAgent by @itsthemoon in #121
• feat: add more tool-calling enabled agents by @dongyuanjushi in #132
• docs: update README.md by @dongyuanjushi in #135
• docs: Added documentation in several directories and comments in each file by @om-raheja in #138
• chore: add pyopenagi install from pypi and locally by @dongyuanjushi in #139
• chore: move external tool API dependencies into the pyopenagi by @dongyuanjushi in #141
• feat: add vllm support by @dongyuanjushi in #142
• feat: add function calling for open-sourced models by @dongyuanjushi in #144
• fix: add output parsers for huggingface llm by @dongyuanjushi in #145
• feat: add vllm multi-gpu inference support by @dongyuanjushi in #146
• refactor: fix unused vars and imports by @odysa in #147
• v0.0.1 by @dongyuanjushi in #149
• v0.0.1.post1 by @dongyuanjushi in #150
• chore: update rules of publish to PyPI only after creating a github tag by @dongyuanjushi in #151
• chore: better lint ci and pre-commit by @odysa in #152
• feat: add output token limit for ollama by @dongyuanjushi in #153
• Fixed aios not working in ollama mode by @wawa0210 in #154
• feat: add function calling support of gemini models by @dongyuanjushi in #155
• docs: add template for raising github issues by @dongyuanjushi in #156
• docs: add bug report template by @dongyuanjushi in #157
• docs: require contributors to use one of the bug templates by @BRama10 in #158
• docs: add pull request template by @dongyuanjushi in #159
• fix: mv vllm to cuda-enable requirement file and update Dockerfile by @dongyuanjushi in #160
• feat: add agent upload/download by @dongyuanjushi in #161
• docs: add website doc template using readthedocs by @dongyuanjushi in #162
• fix: incorrect agent task path for eval and missing reqs for docs by @dongyuanjushi in #163
• feat: created AIOS runtime template by @BRama10 in #164
• docs: add guide of installation and usage by @dongyuanjushi in #165
• fix: invalid link of quickstart by @dongyuanjushi in #166
• feat: add support for claude-3-5-sonnet-20240620 by @jroell in #167
• docs: updating the readme to include recent milestones of the project by @evison in #169
• chore: add pre-commit as necessity in PR template by @dongyuanjushi in #168
• docs: updating the readme to fix minor spelling error by @evison in #170
• fix: correct the json error for gpt4 by @Zhang-Henry in #171
• refactor: move pyopenagi and disentangle queue from agents by @dongyuanjushi in #172
• fix: workflow index error by @dongyuanjushi in #173
• fix: rm unused queues by @dongyuanjushi in #174
• docs: update dot-env by @dongyuanjushi in #175
• docs: add list available agents by @dongyuanjushi in #176
• fix: ollama fc issues by @dongyuanjushi in #177
• perf: remove excess llm cores by @BRama10 in #178
• fix: json decoding error in workflow and tool call by @dongyuanjushi in #179
• docs: add comment templates for autodoc by @dongyuanjushi in #180
• docs: update documentation of llms and external tools by @dongyuanjushi in #184
• refactor: eval script and list_agent script by @dongyuanjushi in #183
• docs: add the documentation tag to readme by @evison in #185
• fix: incorrect api name by @WujiangXu in #186
• docs: fix the documentation tag color in readme by @evison in #187
• fix: add tool_index.template for tool doc generation by @dongyuanjushi in #189
• docs: update readme by @evison in #191
• fix memory_clear bug by @bruceEeZhao in #193
• docs: update README.md by @YuanBoXie in #194
• fix: change decoding to match both list and json object by @dongyuanjushi in #195
• refactor: revise system prompt for generating workflow in react agent by @dongyuanjushi in #197
• feat: add more example agents by @dongyuanjushi in #198
• AIOS Modularization Pt.1: Functional Components by @BRama10 in #199
• feat: add travel planner agent by @2020-qqtcg in #201
• feat: web ui by @BRama10 in #203
• feat: local runtime linked to AIOS by @BRama10 in #202
• Revert "feat: web ui" due to the exposed grok token by @dongyuanjushi in #204
• fix agent output path by @dongyuanjushi in #205
• Web UI by @BRama10 in #206
• Web UI - Bug Fix by @BRama10 in #207
• feat: web ui connection with core AIOS by @BRama10 in #208
• added repl by @MikeyBeez in #209
• feat: agent parser by @BRama10 in #210
• feat: upgraded web ui by @BRama10 in #211
• fix gpt tool calling params by @dongyuanjushi in #212
• feat: remote deployment by @BRama10 in #215
• [feat] Transcription Agent example! by @om-raheja in #213
• feat: autogen adapter by @2020-qqtcg in #216
• feat: remote ui connection by @BRama10 in #217
• remove sleep of gpt llm and fix unset agent id by @dongyuanjushi in #218
• Upgraded & Professional Web UI by @BRama10 in #219
• Polished UI + Faster Inference Times by @BRama10 in #220
• docs: autogen for aios doc by @2020-qqtcg in #221
• bug: revert main page to modern styling by @BRama10 in #222
• feat: add agenthub by @evison in #223
• feat: add open-interpreter adapter by @2020-qqtcg in #224
• [feat] improved tui by @om-raheja in #225
• rm and relocate files in the root directory by @dongyuanjushi in #226
• docs: update readme by @evison in #227
• docs: update readme by @evison in #229
• feat: metagpt adapter by @2020-qqtcg in #230
• docs: update readme by @evison in #231
• docs: update readme by @evison in #232
• docs: update readme by @evison in #233
• docs: update readme by @evison in #234
• refactor code in the root directory by @dongyuanjushi in #235
• fix ID recycler for agent process by @dongyuanjushi in #236
• Hub Deploy by @BRama10 in #237
• rm redundant files by @dongyuanjushi in #239
• feat: agenthub manager connection by @BRama10 in #240
• Refactor thread to enable track of ID by @dongyuanjushi in #241
• revert agenthub manager by @dongyuanjushi in #243
• Main Agenthub Deploy by @BRama10 in #244
• Agent Hub Fixes by @BRama10 in #245
• Home page transfer by @BRama10 in #246
• feat: add aios_stater by @2020-qqtcg in #247
• Homepage Fixes by @BRama10 in #248
• linter by @BRama10 in #249
• add constrains on the step execution and workflow generation by @dongyuanjushi in #250
• ui changes by @BRama10 in #251
• force agent upload with metadata in config.json by @dongyuanjushi in #252
• Final homepage by @BRama10 in #253
• Final homepage by @BRama10 in #254
• Aios deploy by @BRama10 in #255
• minor ui changes by @BRama10 in #256
• Refactor docs by @dongyuanjushi in #257
• update docs by @dongyuanjushi in #258
• aios ui polishes + bug fix for agenthub by @BRama10 in #259
• docs: fix the documentation link by @evison in #260
• fix localhost url by @dongyuanjushi in #261
• fix agent dependencies and add verification of Query and Response by @dongyuanjushi in #263
• feat: cerebrum api routes by @BRama10 in #264
• replace iterative response listener with event signal by @dongyuanjushi in #265
• fix sdk adapter by @2020-qqtcg in #268
• feat: init command interact by @2020-qqtcg in #269
• feat: add installer (unix-like and windows) by @dongyuanjushi in #270
• docs: update installer and docs by @dongyuanjushi in #271
• [feat] fixed agent_repl by @om-raheja in #272
• fix: Resolve log_mode issue in aios_starter() function by @XiangZhang-zx in #274
• fix agent id allocation by @dongyuanjushi in #276
• merge the v0.1.0 from the forked version to agiresearch by @dongyuanjushi in #292

New Contributors

• @peteryschneider made their first contribution in #9
• @eltociear made their first contribution in #11
• @agiresearch made their first contribution in #16
• @JHSUYU made their first contribution in #18
• @1tylermitchell made their first contribution in #19
• @evison made their first contribution in #42
• @JGalego made their first contribution in #48
• @lumiere-ml made their first contribution in #58
• @ivanbelenky made their first contribution in #69
• @JUSTSUJAY made their first contribution in #81
• @Tata0703 made their first contribution in #94
• @zzfoo made their first contribution in #111
• @ArnoldIOI made their first contribution in #118
• @itsthemoon made their first contribution in #122
• @om-raheja made their first contribution in #138
• @odysa made their first contribution in #147
• @wawa0210 made their first contribution in #154
• @jroell made their first contribution in #167
• @Zhang-Henry made their first contribution in #171
• @WujiangXu made their first contribution in #186
• @bruceEeZhao made their first contribution in #193
• @YuanBoXie made their first contribution in #194
• @MikeyBeez made their first contribution in #209

Full Changelog: https://github.com/agiresearch/AIOS/commits/v0.1.0